基于随机森林算法的叠前流体识别

doi:10.7623/syxb202203005

石油学报 ›› 2022, Vol. 43 ›› Issue (3): 376-385.DOI: 10.7623/syxb202203005

基于随机森林算法的叠前流体识别

何健^1,2, 文晓涛^1,2, 李波^1,2, 陈芊澍^1,2, 李垒^1,2

1. 成都理工大学地球勘探与信息技术教育部重点实验室四川成都 610059;
2. 成都理工大学地球物理学院四川成都 610059

收稿日期:2020-07-19 修回日期:2021-09-28 发布日期:2022-04-06
通讯作者: 文晓涛,男,1976年5月生,2006年获成都理工大学地球探测与信息技术专业博士学位,现为成都理工大学地球物理学院教授,主要从事油气储层综合预测方面的研究工作。Email:wenxiaotao@cdut.cn
作者简介:何健,男,1991年3月生,2020年获成都理工大学地球探测与信息技术专业硕士学位,现为成都理工大学地球探测与信息技术专业博士研究生,主要从事地球物理勘探相关工作。Email:963395704@qq.com
基金资助:
国家自然科学基金项目(No.41774142)和国家科技重大专项(2016ZX05002-004-013)资助。

The pre-stack fluid identification method based on random forest algorithm

He Jian^1,2, Wen Xiaotao^1,2, Li Bo^1,2, Chen Qianshu^1,2, Li Lei^1,2

1. Key Laboratory of Earth Exploration and Information Technology, Ministry of Education, Chengdu University of Technology, Sichuan Chengdu 610059, China;
2. Institute of Geophysics, Chengdu University of Technology, Sichuan Chengdu 610059, China

Received:2020-07-19 Revised:2021-09-28 Published:2022-04-06

摘要/Abstract

摘要： 虽然叠前反演技术能够获得多种流体识别因子,但是仅利用单一的流体识别因子进行储层预测通常会带来多解性问题。目前根据多种流体识别因子对储层进行综合解释已成为一种新的趋势,但大部分方法对专家及其经验存在较强的依赖。鉴于此,将随机森林算法引入储层流体识别。首先基于测井数据优选输入特征(流体识别因子),并分别研究输入特征数量和不同特征组合对算法预测结果的影响;然后利用该算法对输入特征与井中储层信息之间的非线性关系进行学习;最后根据学习结果对储层进行综合判别,实现多种流体识别因子的综合利用。该算法削弱了单一流体识别因子所引起的多解性,提高了储层流体识别的精度与可靠性。应用实例表明,通过随机森林算法对5种流体识别因子与井中储层信息进行综合学习,达到了对含气储层和含水储层进行准确识别的目的。

关键词: 叠前反演, 多解性, 流体识别, 综合解释, 随机森林

Abstract: Although pre-stack inversion technology can be used to obtain multiple fluid identification factors, multi-solutions are generally caused by reservoir prediction using a single fluid identification factor. At present, the comprehensive interpretation of reservoir based on various fluid identification factors has become a new trend, of which most methods rely on experts and their experience. Therefore, the random forest algorithm is introduced into reservoir fluid identification. Firstly, the input features (fluid identification factors) are selected based on logging data, and the effects of the number of input features and different feature combinations on the prediction results are studied. Then the algorithm is used to learn the nonlinear relationship between the input features and the reservoir information of the well. Finally, according to the obtained results, a comprehensive analysis is performed on the reservoir, thus realizing the integrated utilization of a large number of fluid identification factors. The algorithm weakens the multi-solution caused by a single fluid identification factor, and improves the accuracy and reliability of reservoir fluid identification. The application examples show that five kinds of fluid identification factors and reservoir information in wells are comprehensively explored using random forest algorithm, achieving the accurate identification of gas and water in underground reservoirs.

Key words: pre-stack inversion, multi-solution, fluid identification, comprehensive explanation, random forest

中图分类号:

P631.4

何健, 文晓涛, 李波, 陈芊澍, 李垒. 基于随机森林算法的叠前流体识别[J]. 石油学报, 2022, 43(3): 376-385.

He Jian, Wen Xiaotao, Li Bo, Chen Qianshu, Li Lei. The pre-stack fluid identification method based on random forest algorithm[J]. Acta Petrolei Sinica, 2022, 43(3): 376-385.

参考文献

[1] 李景叶,陈小宏.基于地震资料的储层流体识别[J].石油学报,2008,29(2):235-238.
LI Jingye,CHEN Xiaohong.Reservoir fluid identification based on seismic data[J].Acta Petrolei Sinica,2008,29(2):235-238.
[2] 杨培杰,印兴耀.非线性二次规划贝叶斯叠前反演[J].地球物理学报,2008,51(6):1876-1882.
YANG Peijie,YIN Xingyao.Non-linear quadratic programming Bayesian prestack inversion[J].Chinese Journal of Geophysics,2008,51(6):1876-1882.
[3] SMITH G C,GIDLOW P M.Weighted stacking for rock property estimation and detection of gas[J].Geophysical Prospecting,1987,35(9):993-1014.
[4] 郝前勇,印兴耀,王玉梅,等.弹性模量流体因子在永新工区储层预测中的应用[J].石油物探,2012,51(5):502-507.
HAO Qianyong,YIN Xingyao,WANG Yumei,et al.Application of elastic modulus fluid factor on reservoir prediction at Yongxin block[J].Geophysical Prospecting for Petroleum,2012,51(5):502-507.
[5] GOODWAY B,CHEN Taiwen,DOWNTON J.Improved AVO fluid detection and lithology discrimination using Lamé petrophysical parameters; "λρ","μρ",& "λ/μ fluid stack",from P and S inversions[J].SEG Technical Program Expanded Abstracts,1997,16(1):183-186.
[6] 印兴耀,张世鑫,张繁昌,等.利用基于Russell近似的弹性波阻抗反演进行储层描述和流体识别[J].石油地球物理勘探,2010,45(3):373-380.
YIN Xingyao,ZHANG Shixin,ZHANG Fanchang,et al.Utilizing Russell approximation-based elastic wave impedance inversion to conduct reservoir description and fluid identification[J].Oil Geophysical Prospecting,2010,45(3):373-380.
[7] 宗兆云,印兴耀,张峰,等.杨氏模量和泊松比反射系数近似方程及叠前地震反演[J].地球物理学报,2012,55(11):3786-3794.
ZONG Zhaoyun,YIN Xingyao,ZHANG Feng,et al.Reflection coefficient equation and pre-stack seismic inversion with Young's modulus and Poisson ratio[J].Chinese Journal of Geophysics,2012,55(11):3786-3794.
[8] 贾凌云,李琳,王千遥,等.基于广义弹性阻抗的流体识别因子反演方法研究与应用[J].石油物探,2018,57(2):302-311.
JIA Lingyun,LI Lin,WANG Qianyao,et al.Fluid identification factor inversion based on generalized elastic impedance[J].Geophysical Prospecting for Petroleum,2018,57(2):302-311.
[9] 陈习峰,王丽,赵国辉.纵横波波阻抗在识别含油砂体中的应用[J].石油物探,2004,43(S1):81-83.
CHEN Xifeng,WANG Li,ZHAO Guohui.Application of longitudinal and transverse wave impedance in identifying oil-bearing sand bodies[J].Geophysical Prospecting for Petroleum,2004,43(S1):81-83.
[10] 罗宁,刘子平,殷增华,等.利用纵横波速度比判断储层流体性质[J].测井技术,2008,32(4):331-333.
LUO Ning,LIU Ziping,YIN Zenghua,et al.Identifying reservoir fluid nature with the ratio of compressional wave velocity to shear wave velocity[J].Well Logging Technology,2008,32(4):331-333.
[11] 陈湛文,尹峰,李幼铭,等.弹性介质中密度ρ与拉梅常数λ、μ的衍射层析成像方法研究[J].地球物理学报,1995,38(2):234-242.
CHEN Zhanwen,YIN Feng,LI Youming,et al.Study of diffraction tomography method for density ρ and lame coefficients λ,μ in elastic media[J].Chinese Journal of Geophysics,1995,38(2):234-242.
[12] QUAKENBUSH M,SHANG B,TUTTLE C.Poisson impedance[J].The Leading Edge,2006,25(2):128-138.
[13] 黄凯,徐群洲,杨晓海,等.纵、横波在岩石中的传播速度比及弹性模量与岩石所含流体的关系[J].新疆石油地质,1998,19(5):369-371.
HUANG Kai,XU Qunzhou,YANG Xiaohai,et al.The relationship between P- and S- wave velocity ratio,modulus of elasticity and fluids contained in rocks[J].Xinjiang Petroleum Geology,1998,19(5):369-371.
[14] 宁忠华,贺振华,黄德济.基于地震资料的高灵敏度流体识别因子[J].石油物探,2006,45(3):239-241.
NING Zhonghua,HE Zhenhua,HUANG Deji.High sensitive fluid identification based on seismic data[J].Geophysical Prospecting for Petroleum,2006,45(3):239-241.
[15] RUSSELL B H,HEDLIN K,HILTERMAN F J,et al.Fluid-property discrimination with AVO:a Biot-Gassmann perspective[J].Geophysics, 2003,68(1):29-39.
[16] 吴建发,赵圣贤,范存辉,等.川南长宁地区龙马溪组富有机质页岩裂缝发育特征及其与含气性的关系[J].石油学报,2021,42(4):428-446.
WU Jianfa,ZHAO Shengxian,FAN Cunhui,et al.Fracture characteristics of the Longmaxi Formation shale and its relationship with gas-bearing properties in Changning area,southern Sichuan[J].Acta Petrolei Sinica,2021,42(4):428-446.
[17] 董平川,徐衍彬,李飞,等.储层裂缝识别和预测方法[J].大庆石油地质与开发,2010,29(2):5-12.
DONG Pingchuan,XU Yanbin,LI Fei,et al.Identification and prediction of reservoir fractures[J].Petroleum Geology and Oilfield Development in Daqing,2010,29(2):5-12.
[18] 杨笑,王志章,周子勇,等.基于参数优化AdaBoost算法的酸性火山岩岩性分类[J].石油学报,2019,40(4):457-467.
YANG Xiao,WANG Zhizhang,ZHOU Ziyong,et al.Lithology classification of acidic volcanic rocks based on parameter-optimized AdaBoost algorithm[J].Acta Petrolei Sinica,2019,40(4):457-467.
[19] 高文彬,李宜强,何书梅,等.基于荧光薄片的剩余油赋存形态分类方法[J].石油学报,2020,41(11):1406-1415.
GAO Wenbin,LI Yiqiang,HE Shumei,et al.Classification method of occurrence mode of remaining oil based on fluorescence thin sections[J].Acta Petrolei Sinica,2020,41(11):1406-1415.
[20] ALP M,CIGIZOGLU H K.Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data[J].Environmental Modelling & Software,2007,22(1):2-13.
[21] CHOI S,JIANG Zhongwei.Cardiac sound murmurs classification with autoregressive spectral analysis and multi-support vector machine technique[J].Computers in Biology and Medicine,2010,40(1):8-20.
[22] BAHRAMMIRZAEE A.A comparative survey of artificial intelligence applications in finance:artificial neural networks,expert system and hybrid intelligent systems[J].Neural Computing and Applications,2010,19(8):1165-1195.
[23] ZOU Zhibin,PENG Hong,LUO Linkai.The application of random forest in finance[J].Applied Mechanics and Materials,2015,740:947-951.
[24] CHEN T,WANG Yucheng.Estimating simulation workload in cloud manufacturing using a classifying artificial neural network ensemble approach[J].Robotics and Computer-Integrated Manufacturing,2016,38:42-51.
[25] 李文秀,文晓涛,李天,等.近似支持向量机的AVO类型判别[J].石油地球物理勘探,2018,53(5):969-974.
LI Wenxiu,WEN Xiaotao,LI Tian,et al.AVO types discrimination based on a proximal support vector machine[J].Oil Geophysical Prospecting,2018,53(5):969-974.
[26] ASIM K M,AWAIS M,MARTNEZ-LVAREZ F,et al.Seismic activity prediction using computational intelligence techniques in northern Pakistan[J].Acta Geophysica,2017,65(5):919-930.
[27] 张银德,童凯军,郑军,等.支持向量机方法在低阻油层流体识别中的应用[J].石油物探,2008,47(3):306-310.
ZHANG Yinde,TONG Kaijun,ZHENG Jun,et al.Application of support vector machine method for identifying fluid in low-resistivity oil layers[J].Geophysical Prospecting for Petroleum,2008,47(3):306-310.
[28] 汪佳蓓,黄捍东.基于BP神经网络的叠前流体识别方法[J].成都理工大学学报:自然科学版,2016,43(6):663-670.
WANG Jiabei,HUANG Handong.Study of pre-stack fluid identification method based on BP neural network[J].Journal of Chengdu University of Technology:Science & Technology Edition,2016,43(6):663-670.
[29] 方匡南.随机森林组合预测理论及其在金融中的应用[M].厦门:厦门大学出版社,2012.
FANG Kuangnan.Random forest combination forecasting theory and its application in finance[M].Xiamen:Xiamen University Press,2012.
[30] 赵艳红,姜汉桥,李洪奇.注水开发油田注水通道状态辨识及预测方法[J].石油学报,2021,42(8):1081-1090.
ZHAO Yanhong,JIANG Hanqiao,LI Hongqi.Identification and predictions of water injectivity for water injection channels in water injection development oilfield[J].Acta Petrolei Sinica,2021,42(8):1081-1090.
[31] 宋建国,杨璐,高强山,等.强容噪性随机森林算法在地震储层预测中的应用[J].石油地球物理勘探,2018,53(5):954-960.
SONG Jianguo,YANG Lu,GAO Qiangshan,et al.Strong tolerance random forest algorithm in seismic reservoir prediction[J].Oil Geophysical Prospecting,2018,53(5):954-960.
[32] 王志宏,韩璐,戚磊.随机森林分类方法在储层岩性识别中的应用[J].辽宁工程技术大学学报:自然科学版,2015,34(9):1083-1088.
WANG Zhihong,HAN Lu,QI Lei.Random forest classification method in the application of reservoir lithology recognition[J].Journal of Liaoning Technical University:Natural Science,2015,34(9):1083-1088.
[33] 温廷新,张波,邵良杉.煤与瓦斯突出预测的随机森林模型[J].计算机工程与应用,2014,50(10):233-237.
WEN Tingxin,ZHANG Bo,SHAO Liangshan.Prediction of coal and gas outburst based on random forest model[J].Computer Engineering and Applications,2014,50(10):233-237.
[34] 陈相府,安西峰.地震横波勘探及其在浅层岩土分层中的应用[J].地球物理学进展,2007,22(5):1655-1659.
CHEN Xiangfu,AN Xifeng.Application of seismic shear wave detection in dividing shallow strata of rock and soil[J].Progress in Geophysics,2007,22(5):1655-1659.
[35] BREIMAN L.Random forests[J].Machine Learning, 2001,45(1):5-32.
[36] BREIMAN L.Bagging predictors[J].Machine Learning, 1996,24(2):123-140.
[37] KUSHARY D.Bootstrap methods and their application[J].Technometrics, 2000,42(2):216-217.
[38] 马中高,朱立华,张卫华,等.雷州半岛南部玄武岩岩石物理特征[J].石油学报,2020,41(6):702-710.
MA Zhonggao,ZHU Lihua,ZHANG Weihua,et al.Petrophysical characteristics of basalt in the southern Leizhou peninsula[J].Acta Petrolei Sinica,2020,41(6):702-710.
[39] AKILADEVI R,NANDHINI D B,NIVESH K V,et al.Prediction and analysis of pollutant using supervised machine learning[J].International Journal of Recent Technology and Engineering,2020,9(2):50-54.
[40] ZHANG Qiang,FU Fengchen,TIAN Ran.A deep learning and image-based model for air quality estimation[J].Science of the Total Environment,2020,724:138178.
[41] 汪跃龙,李凌云,贺艳,等.近钻头钻具姿态测量的多传感器最小二乘原理加权融合方法[J].石油学报,2021,42(4):500-507.
WANG Yuelong,LI Lingyun,HE Yan,et al.A multi-sensor weighted least squares weighted fusion method for attitude measurement of near-bit drilling tool[J].Acta Petrolei Sinica,2021,42(4):500-507.
[42] 沈怀磊,秦长文,王东东,等.琼东南盆地崖城组煤层的识别方法[J].石油学报,2010,31(4):586-590.
SHEN Huailei,QIN Changwen,WANG Dongdong,et al.Distinguishing methods for coal beds in Yacheng Formation of Qiongdongnan Basin[J].Acta Petrolei Sinica,2010,31(4):586-590.
[43] GENUER R,POGGI J M,TULEAU-MALOT C.Variable selection using random forests[J].Pattern Recognition Letters,2010,31(14):2225-2236.
[44] MOUSAVI S M,ZHU Weiqiang,SHENG Yixiao,et al.CRED:a deep residual network of convolutional and recurrent units for earthquake signal detection[J].Scientific Reports,2019,9(1):10267.
[45] ZOU K H,O'MALLEY A J,MAURI L.Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models[J].Circulation,2007,115(5):654-657.
[46] 谢宏宇,侯艳,李康.基于正则化回归的组学数据变量筛选方法[J].中国卫生统计,2016,33(4):733-736.
XIE Hongyu,HOU Yan,LI Kang.A method of selecting group data variables based on regularization regression[J].Chinese Journal of Health Statistics,2016,33(4):733-736.
[47] ADLER J,PARMRYD I.Quantifying colocalization by correlation:the Pearson correlation coefficient is superior to the Mander's overlap coefficient[J].Cytometry Part A,2010,77(8):733-742.

基于随机森林算法的叠前流体识别

The pre-stack fluid identification method based on random forest algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	赵艳红, 姜汉桥, 李洪奇. 注水开发油田注水通道状态辨识及预测方法[J]. 石油学报, 2021, 42(8): 1081-1090.
[2]	马中高, 朱立华, 张卫华, 刘厚裕, 王猛. 雷州半岛南部玄武岩岩石物理特征[J]. 石油学报, 2020, 41(6): 702-710.
[3]	何昌龙, 吕龑, 黄天俊, 李益, 郗诚, 钟光海, 吴仕虎, 杨广广, 干大勇. 基于岩石物理分析的页岩气叠前预测方法在川南威远地区的应用[J]. 石油学报, 2020, 41(10): 1209-1218.
[4]	刘军, 刘杰, 曹均, 文晓涛, 徐乐意, 陈人杰, 陈兆明. 基于岩石物理实验的储层与孔隙流体敏感参数特征——以珠江口盆地东部中-深层碎屑岩储层为例[J]. 石油学报, 2019, 40(s1): 197-205.
[5]	逯宇佳, 曹俊兴, 刘哲哿, 田仁飞, 肖学. 波形分类技术在缝洞型储层流体识别中的应用[J]. 石油学报, 2019, 40(2): 182-189.
[6]	刘志杰, 范宜仁, 曹军涛, 肖承文, 邓少贵, 葛新民, 蔡德洋, 别康. 基于地应力校正的变胶结指数饱和度计算方法——以库车前陆盆地A井区为例[J]. 石油学报, 2018, 39(7): 814-823.
[7]	李坤, 印兴耀, 宗兆云. 基于匹配追踪谱分解的时频域FAVO流体识别方法[J]. 石油学报, 2016, 37(6): 777-786.
[8]	夏义平　徐礼贵　温铁民　张延庆　王贵重. 叠前偏移及储层预测技术研发进展与应用[J]. 石油学报, 2012, 33(S1): 132-141.
[9]	沈凤, 钱绍新, 刘雯林, 韩文杰. AVO多参数反演在气层检测和储层定量研究中的应用[J]. 石油学报, 1994, 15(2): 11-20.
[10]	信荃麟, 刘泽蓉, 侯加根. 薄砂体解释及其成功的应用[J]. 石油学报, 1991, 12(4): 1-10.