Facies-controlled porosity prediction of sandstone reservoirs based on semi-supervised Gaussian mixture model and gradient boosting tree
WEI Guohua1, HAN Hongwei1, LIU Haojie1, LI Mingxuan2, YUAN Sanyi2
1. Shengli Geophysical Research Institute of Sinopec, Dongying, Shandong 257000, China; 2. State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing 102249, China
Abstract:Porosity is an important parameter to describe the physical properties of reservoirs.Considering the obvious differences in the porosity of sandstone and mudstone,this paper proposes a new method for facies-controlled porosity prediction that combines a semi-supervised Gaussian mixture model and a gradient boosting tree to achieve the fine porosity description of sandstone reservoirs.First,a small amount of logging data with lithofacies labels is used to determine the initial cluster center of the Gaussian mixture model and the corresponding lithofacies types.Then,a large amount of unlabeled logging data is used to optimize the Gaussian mixture model so that sandstone and mudstone can be classified correctly.Depending on geological knowledge,the mudstone porosity is interpreted as a fixed minimum value,and only sandstone porosity is predicted subsequently.The porosity prior information and logging sensitive attributes derived from logging curve fitting are taken as the multiva-riate input information of the gradient boosting tree algorithm,and the calculation model of sandstone porosity is built by learning the statistical petrophysical relationship.Finally,according to the lithofacies results,the porosity of the sandstone section and the mudstone section is combined to obtain the facies-controlled porosity.The method is tested with the data of 18 wells in Oilfield D.The results show that the lithofacies classification effect of the semi-supervised Gaussian mixture model is better than those of K-means,support vector machine,random forest,and other machine learning algorithms,and the lithofacies classification accuracy of two blind wells reaches 94.5%.In addition,the facies-controlled porosity predicted by the proposed method in two blind wells is highly consistent with the true porosity with an average correlation coefficient of 0.805.
ANGELERI G P,CARPI R.Porosity prediction from seismic data[J].Geophysical Prospecting,1982,30(5):580-607.
[2]
DOYEN P M.Porosity from seismic data:a geostatistical approach[J].Geophysics,1988,53(10):1263-1275.
[3]
LEITE E P,VIDAL A C.3D porosity prediction from seismic inversion and neural networks[J].Computers & Geosciences,2011,37(8):1174-1180.
[4]
韩学辉,张浩,毛新军,等.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[J].地球物理学报,2021,64(1):289-297.HAN Xuehui,ZHANG Hao,MAO Xinjun,et al.A method of gas porosity measurement for tight reservoirs based on mechanical analysis of core chamber[J].Chinese Journal of Geophysics,2021,64(1):289-297.
[5]
邓继新,王欢,周浩,等.龙马溪组页岩微观结构、地震岩石物理特征与建模[J].地球物理学报,2015,58(6):2123-2136.DENG Jixin,WANG Huan,ZHOU Hao,et al.Microtexture,seismic rock physical properties and modeling of Longmaxi Formation shale[J].Chinese Journal of Geophysics,2015,58(6):2123-2136.
[6]
KHAKSAR A,GRIFFITHS C M.Porosity form so-nic log in gas-bearing shaly sandstones:field data versus empirical equations[J].Exploration Geophysics,1998,29(3-4):440-446.
[7]
未晛,杨志芳,晏信飞,等.改进型随机斑块饱和模型及其在致密气层检测中的应用[J].石油地球物理勘探,2018,53(6):1227-1234.WEI Xian,YANG Zhifang,YAN Xinfei,et al.Modified continuous random patchy-saturation model in tight gas detection[J].Oil Geophysical Prospecting,2018,53(6):1227-1234.
[8]
LUO Y N,HUANG H D,JAKOBSEN M,et al.Prediction of porosity and gas saturation for deep-buried sandstone reservoirs from seismic data using an improved rock-physics model[J].Acta Geophysica,2019,67(2):557-575.
[9]
LI H B,ZHANG J J.Well log and seismic data analysis for complex pore-structure carbonate reservoir using 3D rock physics templates[J].Journal of Applied Geophysics,2018,151:175-183.
[10]
WANG P,CHEN X H,LI J Y,et al.Accurate porosity prediction for tight sandstone reservoir:a case study from North China[J].Geophysics,2020,85(2):B35-B47.
[11]
ARCHIE G E.The electrical resistivity log as an aid in determining some reservoir characteristics[J].Transactions of the AIME,1942,146(1):54-62.
[12]
牛聪,张益明,王迪,等.LA地区盒8段优质储层的特征与分布预测[J].石油地球物理勘探,2017,52(3):591-598.NIU Cong,ZHANG Yiming,WANG Di,et al.Prediction of high-quality reservoir characteristics and distribution in the area LA[J].Oil Geophysical Prospecting,2017,52(3):591-598.
[13]
AVSETH P,LEHOCKI I,KJØSNES Ø,et al.Data-driven rock physics analysis of North Sea tertiary re-servoir sands[J].Geophysical Prospecting,2021,69(3):608-621.
[14]
BACHRACH R.Joint estimation of porosity and sa-turation using stochastic rock-physics modeling[J].Geophysics,2006,71(5):O53-O63.
[15]
GRANA D.Probabilistic approach to rock physics modeling[J].Geophysics,2014,79(2):D123-D143.
[16]
ZHANG Z,ZHANG H,LI J,et al.Permeability and porosity prediction using logging data in a heterogeneous dolomite reservoir:an integrated approach[J].Journal of Natural Gas Science and Engineering,2021,86:103743.
[17]
YASIN Q,SOHAIL G M,KHALID P,et al.Application of machine learning tool to predict the porosity of clastic depositional system,Indus Basin,Pakistan[J].Journal of Petroleum Science and Engineering,2021,197:107975.
[18]
YU H,CHEN G X,GU H M.A machine learning methodology for multivariate pore-pressure prediction[J].Computers & Geosciences,2020,143:104548.
[19]
王光宇,宋建国,徐飞,等.不平衡样本集随机森林岩性预测方法[J].石油地球物理勘探,2021,56(4):679-687.WANG Guangyu,SONG Jianguo,XU Fei,et al.Random forests lithology prediction method for imba-lanced data sets[J].Oil Geophysical Prospecting,2021,56(4):679-687.
[20]
闫星宇,顾汉明,肖逸飞,等.XGBoost算法在致密砂岩气储层测井解释中的应用[J].石油地球物理勘探,2019,54(2):447-455.YAN Xingyu,GU Hanming,XIAO Yifei,et al.XGBoost algorithm applied in the interpretation of tight-sand gas reservoir on well logging data[J].Oil Geophysical Prospecting,2019,54(2):447-455.
[21]
谷宇峰,张道勇,鲍志东.测井资料PSO-XGBoost渗透率预测[J].石油地球物理勘探,2021,56(1):26-37.GU Yufeng,ZHANG Daoyong,BAO Zhidong.Per-meability prediction using PSO-XGBoost based on logging data[J].Oil Geophysical Prospecting,2021,56(1):26-37.
[22]
CHEN L,LIN W B,CHEN P,et al.Porosity prediction from well logs using back propagation neural network optimized by genetic algorithm in one heterogeneous oil reservoirs of Ordos Basin,China[J].Journal of Earth Science,2021,32(4):828-838.
[23]
杨柳青,陈伟,查蓓.利用卷积神经网络对储层孔隙度的预测研究与应用[J].地球物理学进展,2019,34(4):1548-1555.YANG Liuqing,CHEN Wei,ZHA Bei.Prediction and application of reservoir porosity by convolutional neural network[J].Progress in Geophysics,2019,34(4):1548-1555.
[24]
杨午阳,杨佳润,陈双全,等.基于U-Net深度学习网络的地震数据断层检测[J].石油地球物理勘探,2021,56(4):688-697.YANG Wuyang,YANG Jiarun,CHEN Shuangquan,et al.Seismic data fault detection based on U-Net deep learning network[J].Oil Geophysical Prospecting,2021,56(4):688-697.
[25]
CHEN W,YANG L Q,ZHA B,et al.Deep learning reservoir porosity prediction based on multilayer long short-term memory network[J].Geophysics,2020,85(4):WA213-WA225.
[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]
杨怀杰.测井数据的小波分析方法研究——CCSD主孔数据为例[D].北京:中国地质大学(北京),2016.YANG Huaijie.Study on Method of Wavelet Transformation in Geophysical Well Log-Evidence from Chinese Continental Scientific Drilling Main Hole[D].China University of Geosciences(Beijing),Beijing,2016.
[28]
赵军龙,刘建建.常规测井曲线的小波和希尔伯特—黄变换滤波效果分析[J].石油地球物理勘探,2016,51(4):801-808.ZHAO Junlong,LIU Jianjian.Conventional well logging data filtering with wavelet transformation and Hilbert-Huang transformation[J].Oil Geophysical Prospecting,2016,51(4):801-808.
[29]
薛波,杨青,张超虹.基于形态学滤波与小波变换的测井曲线自动分层方法[J].地球物理学进展,2020,35(1):203-210.XUE Bo,YANG Qing,ZHANG Chaohong.Automa-tic stratification method of logging curve based on morphological filtering and wavelet transform[J].Progress in Geophysics,2020,35(1):203-210.
[30]
房文静.测井多尺度分析方法及应用研究[D].山东青岛:中国石油大学(华东),2007.FANG Wenjing.Research on Multi-Scale Analysis and Its Application to Well Logging[D].China University of Petroleum(East China),Qingdao,Shan-dong,2007.
[31]
NOWAKOWSKA E,KORONACKI J,LIPOVETSKY S.Clusterability assessment for Gaussian mixture mo-dels[J].Applied Mathematics and Computation,2015,256:591-601.
[32]
DEMPSTER A P,LAIRD N M,RUBIN D B.Maximum likelihood from incomplete data via the EM algorithm[J].Journal of the Royal Statistical Society:Series B (Methodological),1977,39(1):1-22.