Application of multi-threshold BIRCH clustering to facies-controlled porosity estimation
SUN Qifeng1, DUAN Youxiang1, LIU Fan1, LI Hongqiang2
1. College of Computer Science and Technology, China University of Petroleum(East China), Qingdao, Shandong 266580, China; 2. Drilling Technology Research Institute of Shengli Petroleum Engineering Corporation Limited, SINOPEC, Dongying, Shandong 257000, China
摘要 岩相及孔隙度预测在油气勘探中非常重要,为此,提出一种基于多阈值BIRCH(Balanced Iterative Reducing and Clustering Using Hierarchies)聚类的岩相预测方法,并以此为基础利用岭回归算法预测孔隙度。首先,根据地震波阻抗数据分布规律启发式设定初始阈值,根据簇之间体积的不一致性,动态增加阈值,使用Agglomerative算法进行全局聚类以划分岩相;然后,以井点处孔隙度和地震波阻抗数据为输入,在同一岩相内采用改进的岭回归方法预测孔隙度。模型实验表明,多阈值BIRCH聚类方法具有良好的稳定性和较高的计算效率,岩相划分准确。实际数据结果表明,该方法能够准确预测孔隙度。
Abstract:In view of the importance of lithofacies and porosity study in hydrocarbon exploration,we present an approach of multi-threshold BIRCH clustering for lithofacies classification,based on which we estimate porosity using ridge regression.The heuristic initial threshold is set in terms of wave impedance distribution,and the number of thresholds is increased dynamically according to inter-clustering volume inconsistency.Global Agglomerative clustering is then employed for lithofacies classification.For each lithofacies,a modified ridge regression algorithm is used to predict porosity based on well porosity.Model tests show that multi-threshold BIRCH clustering exhibits good robustness and computational efficiency for accurate lithofacies classification.A field data test shows that porosity could be estimated accurately using this method.
Wang J,Cao Y C,Liu K Y,et al.Identification of se-dimentary-diagenetic facies and reservoir porosity and permeability prediction:An example from the Eocene beach-bar sandstone in the Dongying Depression,China[J].Marine and Petroleum Geology,2017,82:69-84.
[2]
Miller K,Vanorio T,Yang S,et al.A scale-consistent method for imaging porosity and micrite in dual-porosity carbonate rocks[J].Geophysics,2019,84(3):MR115-MR127.
[3]
Álvarez P,Rangel J,Martinez M.Mapping porosity distribution in a vuggy carbonate reservoir integrating seismic attributes with borehole image logs through a supervised facies analysis[C].SEG Technical Program Expanded Abstracts,2009,28:1880-1884.
[4]
Ashraf U,Zhu P M,Yasin Q,et al.Classification of reservoir facies using well log and 3D seismic attributes for prospect evaluation and field development:A case study of Sawan gas field,Pakistan[J].Journal of Petroleum Science and Engineering,2019,175:338-351.
[5]
Xu Y,Yang H,Liu Y,et al.Application of seismic facies and attributes analysis on the identification of Permian igneous rock[J].International Journal of Mining Science and Technology,2012,22(4):471-475.
[6]
朱超,刘占国,杨少勇,等.利用相控分频反演预测英西湖相碳酸盐岩储层[J].石油地球物理勘探,2018,53(4):832-841.ZHU Chao,LIU Zhanguo,YANG Shaoyong,et al.Lacustrine carbonate reservoir prediction in Yingxi,Qaidam Basin with the facies-constrained and segmented-frequency-band inversion[J].Oil Geophysical Prospecting,2018,53(4):832-841.
[7]
井涌泉,栾东肖,张雨晴,等.基于地震属性特征的河流相叠置砂岩储层预测方法[J].石油地球物理勘探,2018,53(5):1049-1058.JING Yongquan,LUAN Dongxiao,ZHANG Yuqing, et al.Fluvial facies inter-bedded sand reservoir prediction with seismic multi-attributes[J].Oil Geophysical Prospecting,2018,53(5):1049-1058.
[8]
de Figueiredo L P,Grana D,Santos M,et al.Bayesian seismic inversion based on rock-physics prior mode-ling for the joint estimation of acoustic impedance,porosity and lithofacies[J].Journal of Computational Physics,2017,336:128-142.
[9]
李金磊,陈祖庆,王良军,等.相控技术在低勘探区生屑滩相储层预测中的应用[J].岩性油气藏,2017,29(3):110-117.LI Jinlei,CHEN Zuqing,WANG Liangjun,et al.Application of facies-controlled technique to bioclastic shoal reservoir prediction in less well zones[J].Lithologic Reservoirs,2017,29(3):110-117.
[10]
王海龙,曲永强,张巧凤,等.松辽盆地深层沙河子组致密砂岩储层预测[J].石油地球物理勘探,2017,52(增刊2):129-134.WANG Hailong,QU Yongqiang,ZHANG Qiaofeng,et al.Tight-sand reservoir prediction in the deep Shahezi formation,Songliao Basin[J].Oil Geophysical Prospecting,2017,52(S2):129-134.
[11]
He J H,Ding W L,Jiang Z X,et al.Logging identification and characteristic analysis of the lacustrine organic-rich shale lithofacies:A case study from the Es3l shale in the Jiyang Depression,Bohai Bay Basin,Eastern China[J].Journal of Petroleum Science and Engineering,2016,145:238-255.
[12]
Saggaf M M,Nebrija E L.A fuzzy logic approach for the estimation of facies from wire-line logs[J].AAPG Bulletin,2003,87(7):1223-1240.
[13]
Wang G C,Carr T R,Ju Y W,et al.Identifying organic-rich Marcellus Shale lithofacies by support vector machine classifier in the Appalachian basin[J].Computers & Geosciences,2014,64:52-60.
[14]
张阳,邱隆伟,李际,等.基于模糊C均值地震属性聚类的沉积相分析[J].中国石油大学学报(自然科学版),2015,39(4):53-61.ZHANG Yang,QIU Longwei,LI Ji,et al.Sedimentary facies analysis based on cluster of seismic attri-butes by fuzzy C-means algorithm[J].Journal of China University of Petroleum (Edition of Natural Science),2015,39(4):53-61.
[15]
庞锐,魏嘉.利用K均值聚类方法进行地震相识别[C].中国地球物理学会第二十四届年会论文集,2008.PANG Rui,WEI Jia.Seismic facies identification using K-means clustering[C]. Proceedings of the 24th Annual Meeting of the Chinese Geophysical Society,2008.
[16]
Irani R,Nasimi R.Evolving neural network using real coded genetic algorithm for permeability estimation of the reservoir[J].Expert Systems with Applications,2011,38(8):9862-9866.
[17]
Tahmasebi P,Javadpour F,Sahimi M.Data mining and machine learning for identifying sweet spots in shale reservoirs[J].Expert Systems with Applications,2017,88:435-447.
[18]
Saffarzadeh S,Shadizadeh S R.Reservoir rock permeability prediction using support vector regression in an Iranian oil field[J].Journal of Geophysics and Engineering,2012,9(3):336-344.
[19]
Pratama H.Machine learning:using optimized KNN (K-Nearest Neighbors) to predict the facies classifications[C].The 13th SEGJ International Symposium,2018,538-541.
[20]
Baziar S,Shahripour H B,Tadayoni M,et al.Prediction of water saturation in a tight gas sandstone re-servoir by using four intelligent methods:a comparative study[J].Neural Computing and Applications,2018,30(4):1171-1185.
[21]
宋建国,高强山,李哲.随机森林回归在地震储层预测中的应用[J].石油地球物理勘探,2016,51(6):1202-1211.SONG Jianguo,GAO Qiangshan and LI Zhe.Application of random forests for regression to seismic reservoir prediction[J].Oil Geophysical Prospecting,2016,51(6):1202-1211.
[22]
Zhang T,Ramakrishnan R,Livny M.BIRCH:a new data clustering algorithm and its applications[J].Data Mining and Knowledge Discovery,1997,1(2):141-182.
[23]
邵峰晶,张斌,于忠清.多阈值BIRCH聚类算法及其应用[J].计算机工程与应用,2004,40(12):174-176.SHAO Fengjing,ZHANG Bin,YU Zhongqing.BIRCH clustering algorithm with muti-threshold[J].Computer Engineering and Applications,2004,40(12):174-176.
[24]
Olson C F.Parallel algorithms for hierarchical clustering[J].Parallel Computing,1995,21(8):1313-1325.
[25]
韦相.基于密度的改进BIRCH聚类算法[J].计算机工程与应用,2013,49(10):201-205.WEI Xiang.Improved BIRCH clustering algorithm based on density[J].Computer Engineering and Applications,2013,49(10):201-205.
[26]
李航.统计学习方法[M].北京:清华大学出版社,2012,21-23.LI Hang.Statistical Learning Method[M].Tsinghua University Press,Beijing,2012,21-23.
[27]
Hoerl A E,Kennard R W.Ridge regression:biased estimation for nonorthogonal problems[J].Technometrics,1970,12(1):55-67.
[28]
王琪,冷林峰,常永莲.改进岭回归与主成分回归的股指跟踪研究[J].重庆理工大学学报(自然科学),2018,(1):212-221.WANG Qi,LENG Linfeng,CHANG Yonglian.Improvement of ridge regression and principal component regression in stock index tracking[J].Journal of Chongqing University of Technology(Natural Science),2018(1):212-221.
[29]
Lee J,Mukerji T.The Stanford VI-E reservoir:A synthetic data set for joint seismic-EM time-lapse monitoring algorithms[C].25th Annual Report,Stanford Center for Reservoir Forecasting,Stanford University,Stanford,CA,2012.
[30]
Steinley D.Properties of the Hubert-Arabie adjusted Rand index[J].Psychological Methods,2004,9(3):386-396.
[31]
张长开,姜秀娣,朱振宇,等.基于支持向量机的属性优选和储层预测[J].石油地球物理勘探,2012,47(2):282-285.ZHANG Changkai,JIANG Xiudi,ZHU Zhenyu,et al.Attributes selection and reservoir prediction based on support vector machine[J].Oil Geophysical Prospecting,2012,47(2):282-285.