基于参数优化AdaBoost算法的酸性火山岩岩性分类

doi:10.7623/syxb201904007

石油学报 ›› 2019, Vol. 40 ›› Issue (4): 457-467.DOI: 10.7623/syxb201904007

基于参数优化AdaBoost算法的酸性火山岩岩性分类

杨笑, 王志章, 周子勇, 魏周城, 曲康, 王翔宇, 王如意

中国石油大学(北京)油气资源与探测国家重点实验室北京 102249

收稿日期:2018-05-14 修回日期:2019-01-24 出版日期:2019-04-25 发布日期:2019-05-07
通讯作者: 王志章,男,1962年9月生,1985年获石油大学(华东)学士学位,1998年获石油大学(北京)博士学位,现为中国石油大学(北京)教授、博士生导师,主要从事油藏描述及预测、油气田开发地质、测录井地质、地震地质方面的教学与科研。Email:whx3998@vip.sina.com
作者简介:杨笑,女,1994年6月生,2016年获西安石油大学学士学位,现为中国石油大学(北京)硕士研究生,主要从事油气田开发研究工作。Email:864126663@qq.com

Lithology classification of acidic volcanic rocks based on parameter-optimized AdaBoost algorithm

Yang Xiao, Wang Zhizhang, Zhou Ziyong, Wei Zhoucheng, Qu Kang, Wang Xiangyu, Wang Ruyi

State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Beijing 102249, China

Received:2018-05-14 Revised:2019-01-24 Online:2019-04-25 Published:2019-05-07

摘要/Abstract

摘要：

岩性识别是火山岩油气藏勘探的基础，为提高长岭气田火山岩岩性识别的准确率，采用决策树、支持向量机、逻辑回归、AdaBoost-决策树、AdaBoost-支持向量机和AdaBoost-逻辑回归6种算法，对研究区酸性火山岩岩性进行分类与识别。通过分析研究区火山岩不同岩性的测井响应特征，选取了对火山岩岩性、组构和孔隙结构反应灵敏的12种岩石物理测井参数作为分类特征量。选择3口井中岩心分析和岩矿录井资料完整的7 150个测井数据作为数据集，并从中随机选取70 % 的数据作为训练集建立岩性识别模型，剩余30 % 的数据作为测试集。对6种算法建立的模型通过交叉验证进行参数优化及模型评价，对比不同算法与录井剖面的结果表明，AdaBoost-决策树算法可作为长岭气田利用常规测井资料识别火山岩岩性的有效手段，准确率可达90 % 以上。

关键词: 火山岩, 岩性识别, 集成算法, AdaBoost算法, 交叉验证

Abstract:

Lithologic identification provides a basis for the exploration of volcanic oil and gas reservoirs. In order to improve the accuracy of lithologic identification of volcanic rocks in Changling gasfield, six machine learning algorithms are used, i.e., decision tree, support vector machine, logistic regression, AdaBoost-DTC, AdaBoost-SVC and AdaBoost-LR, to classify and identify the lithologies of acidic volcanic rocks. After summarizing the logging response characteristics of different volcanic rocks in the study area, 12 kinds of petro-physical logging parameters sensitively reflecting the lithology, fabrics and pore structure of volcanic rocks are selected as classification characteristic variables. A total of 7 150 pieces of logging data with complete core analysis and rocklogging data of three wells are taken as the data set, 70 % of which are randomly selected as the training set to create lithology identification model; the remaining 30 % of the data is taken as a test set. The models established for six algorithms are cross-validated for parameter optimization and model evaluation. Through comparing different algorithms and logging profiles, the results indicate that the AdaBoost-decision tree algorithm is an effective tool using the conventional logging data of Changling gas field to identify the lithologies of volcanic rocks with the accuracy more than 90 %.

Key words: volcanic rock, lithological identification, integrated algorithm, AdaBoost algorithm, cross-validation

中图分类号:

TE19

杨笑, 王志章, 周子勇, 魏周城, 曲康, 王翔宇, 王如意. 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, Wei Zhoucheng, Qu Kang, Wang Xiangyu, Wang Ruyi. Lithology classification of acidic volcanic rocks based on parameter-optimized AdaBoost algorithm[J]. Acta Petrolei Sinica, 2019, 40(4): 457-467.

参考文献

[1] 唐华风,孔坦,刘祥,等.松辽盆地下白垩统沉火山碎屑岩优质储层特征和形成机理[J].石油学报,2016,37(5):631-643.
TANG Huafeng,KONG Tan,LIU Xiang,et al.Characteristics and formation mechanisms of high quality reservoir of the volcaniclastic sedimentary rocks of Early Cretaceous in Songliao Basin[J].Acta Petrolei Sinica,2016,37(5):631-643.
[2] 叶涛,韦阿娟,祝春荣,等.渤海海域基底"改造型火山机构"特征及油气成藏意义[J].石油学报,2016,37(11):1370-1380.
YE Tao,WEI Ajuan,ZHU Chunrong,et al.Characteristics and hydrocarbon accumulation significance of reformed volcanic edifice in the basement of Bohai Sea[J].Acta Petrolei Sinica,2016,37(11):1370-1380.
[3] 陈东旭,章凤奇,陈汉林,等.新生代辉绿岩岩体识别及油气地质意义——以中国东北地区方正断陷为例[J].石油学报,2016,37(6):757-767.
CHEN Dongxu,ZHANG Fengqi,CHEN Hanlin,et al.Identification and hydrocarbon geological significance of Cenozoic diabase rock:a case study of Fangzheng faulted sag,NE China[J].Acta Petrolei Sinica,2016,37(6):757-767.
[4] 胡志伟,徐长贵,杨波,等.渤海海域蓬莱9-1油田花岗岩潜山储层成因机制及石油地质意义[J].石油学报,2017,38(3):274-285.
HU Zhiwei,XU Changgui,YANG Bo,et al.Reservoir forming mechanism of Penglai 9-1 granite buried-hills and its oil geology significance in Bohai Sea[J].Acta Petrolei Sinica,2017,38(3):274-285.
[5] 范宜仁,黄隆基,代诗华.交会图技术在火山岩岩性与裂缝识别中的应用[J].测井技术,1999,23(1):53-56.
FAN Yiren,HUANG longji,DAI Shihua.Application of crossplot technique to the determination of lithology composition and fracture identification of igneous rock[J].Well Logging Technology,1999,23(1):53-56.
[6] 张建民,李超炜,张继业,等.长深1井区火成岩岩性识别方法及应用[J].吉林大学学报:地球科学版,2008,38(S1):106-109.
ZHANG Jianmin,LI Chaowei,ZHANG Jiye,et al.A lithologic identification method of igneous rocks and its application in Changling Area[J].Journal of Jilin University:Earth Science Edition,2008,38(S1):106-109.
[7] 张莹,潘保芝.多种岩性分类方法在火山岩岩性识别中的应用[J].测井技术,2011,35(5):474-478.
ZHANG Ying,PAN Baozhi.Application of various lithologic classification methods to volcanic rock identification[J].Well Logging Technology,2011,35(5):474-478.
[8] 孙圆辉,宋新民,冉启全,等.长岭气田火山岩岩性和岩相特征及其对储集层的控制[J].石油勘探与开发,2009,36(1):68-73.
SUN Yuanhui,SONG Xinmin,RAN Qiquan,et al.Lithologic and lithofacies characteristics of volcanic rock and their control over reservoirs,Changling Casfield[J].Petroleum Exploration and Development,2009,36(1):68-73.
[9] 范存辉,梁则亮,秦启荣,等.基于测井参数的遗传BP神经网络识别火山岩岩性——以准噶尔盆地西北缘中拐凸起石炭系火山岩为例[J].石油天然气学报,2012,34(1):68-71.
FAN Cunhui,LIANG Zeliang,QIN Qirong,et al.Identification of volcanic-rock lithology by using genetic BP neural network based on logging parameters—by taking carboniferous volcanic rocks in Zhongguai uplift of northwestern margin of Junggar Basin for instance[J].Journal of Oil and Gas Technology,2012,34(1): 68-71.
[10] 刘明军,李恒堂,姜在炳.GA-BP神经网络模型在彬长矿区测井岩性识别中的应用[J].煤田地质与勘探,2011,39(4):8-12.
LIU Mingjun,LI Hengtang,JIANG Zaibing.Application of genetic-BP neural network model in lithology identification by logging data in binchang mining are[J].Coal Geology & Exploration,2011,39(4):8-12.
[11] 张莹,潘保芝.基于主成分分析的SOM神经网络在火山岩岩性识别中的应用[J].测井技术,2009,33(6):550-554.
ZHANG Ying,PAN Baozhi.Application of SOM neural network method to volcanic lithology recognition based on principal components analysis[J].Well Logging Technology,2009,33(6):550-554.
[12] 朱怡翔,石广仁.火山岩岩性的支持向量机识别[J].石油学报,2013,34(2):312-322.
ZHU Yixiang,SHI Guangren.Identification of lithologic characteristics of volcanic rocks by support vector machine[J].Acta Petrolei Sinica,2013,34(2):312-322.
[13] 牟丹,王祝文,黄玉龙,等.基于SVM测井数据的火山岩岩性识别——以辽河盆地东部坳陷为例[J].地球物理学报,2015,58(5):1785-1793.
MOU Dan,WANG Zhuwen,HUANG Yulong,et al.Lithological identification of volcanic rocks from SVM well logging data:Case study in the eastern depression of Liaohe Basin[J].Chinese Journal of Geophysics,2015,58(5):1785-1793.
[14] 牟丹,王祝文,黄玉龙,等.基于最小二乘支持向量机测井识别火山岩类型:以辽河盆地中基性火山岩为例[J].吉林大学学报:地球科学版,2015,45(2):639-648.
MOU Dan,WANG Zhuwen,HUANG Yulong,et al.Application of least squares support vector machine to lithology identification:taking intermediate/basaltic rocks of Liaohe Basin as an example[J].Journal of Jilin University:Earth Science Edition,2015,45(2):639-648.
[15] 张莹,潘保芝.松辽盆地火山岩岩性识别中测井数据的选择及判别方法[J].石油学报,2012,33(5):830-834.
ZHANG Ying,PAN Baozhi.Selection and identification of logging data for lithology recognition of volcanic rocks in Songliao Basin[J].Acta Petrolei Sinica,2012,33(5):830-834.
[16] SCHAPIRE R E.The boosting approach to machine learning:an overview[M]//DENISON D D,HANSEN M H,HOLMES C C,et al.Nonlinear Estimation and Classification.New York,NY:Springer,2002.
[17] BREIMAN L.Bagging predictors[J].Machine Learning,1996,24(2):123-140.
[18] OPITZ D,MACLIN R.Popular ensemble methods:an empirical study[J].Journal of Artificial Intelligence Research,1999,11:169-198.
[19] BAUER E,KOHAVI R.An empirical comparison of voting classification algorithms:bagging,boosting,and variants[J].Machine Learning,1999,36(1/2):105-139.
[20] FREUND Y,SCHAPIRE R E.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139.
[21] FREUND Y,IYER R,SCHAPIRE R E,et al.An efficient boosting algorithm for combining preferences[J].Journal of Machine Learning Research,2003,4(6):933-969.
[22] FREUND Y,SCHAPIRE R E.Experiments with a new boosting algorithm[J].International Conference on Machine Learning.1996:148-156.
[23] 曹莹,苗启广,刘家辰,等.AdaBoost算法研究进展与展望[J].自动化学报,2013,39(6):745-758.
CAO Ying,MIAO Qiguang,LIU Jiachen,et al.Advance and prospects of AdaBoost algorithm[J].Acta Automatica Sinica,2013,39(6):745-758.
[24] 朱林奇,张冲.谱聚类-AdaBoost集成数据挖掘算法在岩性识别中的应用[J].中国科技论文,2016,11(5):545-550.
ZHU Linqi,ZHANG Chong.Application of spectral clustering-AdaBoost integrated data mining algorithm in lithology identification[J].Chinese Science Paper,2016,11(5):545-550.
[25] COUCEYRO P R,KOYLU E O,KUHAR M J.Further studies on the anatomical distribution of CART by in situ hybridization[J].Journal of Chemical Neuroanatomy,1997,12(4):229-241.
[26] 周曙光,周可法,崔遥,等.基于逻辑回归模型的化探异常信息识别研究——以克拉玛依地区为例[J].西北地质,2016,49(1):234-240.
ZHOU Shuguang,ZHOU Kefa,CUI Yao,et al.Application of logistic regression methods in geochemical data analysis and mineral exploration:example from karamay region[J].Northwestern Geology,2016,49(1):234-240.
[27] 高兴军,闫林辉,田昌炳,等.长岭气田营城组火山岩储层特征及分类评价[J].天然气地球科学,2014,25(12):1951-1961.
GAO Xingjun,YAN Linhui,TIAN Changbing,et al.Characteristics and classification evaluation of volcanic rock reservoir in Yingcheng formation of Changling gasfield[J].Natural Gas Geoscience,2014,25(12):1951-1961.
[28] LE MAITRE R W.A proposal by the IUGS subcommission on the systematics of igneous rocks for a chemical classification of volcanic rocks based on the total alkali silica (TAS) diagram[J].Australian Journal of Earth Science,1984,31(2):243-255.
[29] 邱家骧.国际地科联火成岩分类学分委会推荐的火山岩分类简介[J].现代地质,1991,5(4):457-468.
QIU Jiaxiang.Brief introduction of a classification of volcanic rocks recommendations of the IUGS subcommission on the systematics of igneous rocks[J].Geoscience,1991,5(4):457-468.
[30] 范宜仁,朱学娟,邓少贵,等.南堡5号构造火山岩岩性识别技术研究[J].地球物理学进展,2012,27(4):1640-1647.
FAN Yiren,ZHU Xuejuan,DENG Shaogui,et al.Research on the technology of lithology identification of volcanic rock in Nanpu 5th structure[J].Progress in Geophysics, 2012,27(4):1640-1647.

基于参数优化AdaBoost算法的酸性火山岩岩性分类

Lithology classification of acidic volcanic rocks based on parameter-optimized AdaBoost algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	支东明, 李建忠, 周志超, 焦立新, 范谭广, 李斌, 梁辉, 王兴刚. 三塘湖盆地油气勘探开发新领域、新类型及资源潜力[J]. 石油学报, 2024, 45(1): 115-132.
[2]	陈亚军, 于家义, 宋小勇, 张中劲, 孟朋飞, 解士建, 焦巧平. 三塘湖盆地马朗凹陷牛圈湖—牛东构造带上石炭统火山岩黏土矿物特征及其对储层物性的影响[J]. 石油学报, 2021, 42(8): 1053-1071.
[3]	王尉, 赵路子, 罗冰, 刘冉, 李亚, 赵立可, 裴森奇, 胡涛. 川西地区二叠系火山岩异常高压演化与天然气成藏的关系[J]. 石油学报, 2021, 42(11): 1437-1445.
[4]	石新朴, 杜果, 杨丹, 周兴燕, 郑玮鸽, 林加恩. 不稳态窜流部分打开压裂井试井分析模型建立及应用[J]. 石油学报, 2021, 42(10): 1357-1363.
[5]	唐华风, 戴岩林, 郭天婵, 刘钊, 何贤培, 张一弛. 侵出式火山机构储层的分布模式——以伊通火山群为例[J]. 石油学报, 2020, 41(7): 809-820.
[6]	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.
[7]	唐华风, 王璞珺, 边伟华, 黄玉龙, 高有峰, 代晓娟. 火山岩储层地质研究回顾[J]. 石油学报, 2020, 41(12): 1744-1773.
[8]	傅宁, 王柯, 贾庆军. “源热共控”北部湾盆地福山凹陷油气的形成[J]. 石油学报, 2019, 40(S2): 38-45.
[9]	王永卓, 周学民, 印长海, 舒萍, 曹宝军, 朱映康. 徐深气田成藏条件及勘探开发关键技术[J]. 石油学报, 2019, 40(7): 866-886.
[10]	张兆辉, 杜社宽, 陈华勇, 于红果. 基于电成像测井的火山岩裂缝分布定量表征——以准噶尔盆地滴西地区石炭系为例[J]. 石油学报, 2018, 39(10): 1130-1140.
[11]	高树生, 胡志明, 刘华勋, 叶礼友, 安为国. 不同岩性储层的微观孔隙特征[J]. 石油学报, 2016, 37(2): 248-256.
[12]	叶涛, 韦阿娟, 祝春荣, 王粤川, 高坤顺, 曾金昌. 渤海海域基底“改造型火山机构”特征及油气成藏意义[J]. 石油学报, 2016, 37(11): 1370-1380,1434.
[13]	祗淑华, 沈华, 安纪星, 田福清, 罗安银, 成捷, 檀玉松, 赵学松, 安霞. 束鹿凹陷沙河街组致密油复杂岩性测井识别技术[J]. 石油学报, 2015, 36(s1): 40-49.
[14]	衣健, 王璞珺, 唐华风, 赵然磊, 姚瑞士, 郝国丽, 高有峰. 火山地层界面的地质属性、地质内涵和储层意义——以中国东北地区中生代—新生代火山岩为例[J]. 石油学报, 2015, 36(3): 324-336.
[15]	王岩泉, 胡大千, 蔡国刚, 王璞珺, 于小健. 辽河盆地东部凹陷火山岩储层特征与主控因素[J]. 石油学报, 2013, 34(5): 896-904.