基于随机森林的K-近邻算法划分火成岩岩性

赖强; 魏伯阳; 吴煜宇; 潘保芝; 谢冰; 郭宇航

doi:10.3969/j.issn.1006-6535.2021.06.008

特种油气藏 >

2021 , Vol. 28 >Issue 6: 62 - 69

DOI: https://doi.org/10.3969/j.issn.1006-6535.2021.06.008

油藏工程

基于随机森林的K-近邻算法划分火成岩岩性

赖强 ,
魏伯阳 ,
吴煜宇 ,
潘保芝 ,
谢冰 ,
郭宇航

展开

1.中国石油西南油气田分公司,四川成都 610041;
2.吉林大学,吉林长春 130026;
3.河南省煤炭地质勘察研究总院,河南郑州 450046

赖强(1979—),男,高级工程师,2002年毕业于西南石油学院应用地球物理专业,2006年毕业于中国石油大学(北京)地球探测与信息技术专业,获硕士学位,现从事测井资料处理及解释方法研究工作。

收稿日期: 2020-10-06

修回日期: 2021-10-13

网络出版日期: 2022-02-16

基金资助

中国石油西南油气田科技重大专项“四川盆地二叠系火成岩成藏地质理论与勘探开发关键技术研究”(2019ZD01-04)

收起

Classification of Igneous Rock Lithology with K-nearest Neighbor Algorithm Based on Random Forest (RF-KNN)

Lai Qiang ,
Wei Boyang ,
Wu Yuyu ,
Pan Baozhi ,
Xie Bing ,
Guo Yuhang

Expand

1. PetroChina Southwest Oil and Gasfield Company, Chengdu, Sichuan 610041, China;
2. Jilin University, Changchun, Jilin 130026, China;
3. Henan General Research Institute of Coal Geology and Exploration, Zhengzhou, Henan 450046, China

Received date: 2020-10-06

Revised date: 2021-10-13

Online published: 2022-02-16

Fold

摘要

针对火成岩油气藏火成岩岩性划分难,岩性划分准确率受薄片鉴定样本数量影响大的问题,利用随机森林(RF)算法分析不同的测井曲线与火成岩岩性相关性,再利用K-近邻(KNN)算法划分小样本薄片鉴定情况下的火成岩岩性。将研究成果应用于川西地区二叠系火成岩地层,结果表明:测井曲线与岩性相关程度从高到低依次为GR、R_t、DEN、CNL、AC;KNN算法划分火成岩岩性,k取值受分类数量和训练样本数量2个因素控制,样本数量较小时后者影响程度大于前者;k为3时,24个火成岩训练样本(5种岩性)KNN法回判准确率为87.5%,14个火成岩(5种岩性)测试样本测试准确率为92.5%。对比图版划分火成岩岩性,KNN算法受人为影响小,参数调节简便。该研究对小样本情况下火成岩岩性划分有重要指导意义。

关键词： 火成岩油气藏; 岩性划分; 薄片鉴定; KNN; 随机森林

本文引用格式

赖强 , 魏伯阳 , 吴煜宇 , 潘保芝 , 谢冰 , 郭宇航 . 基于随机森林的K-近邻算法划分火成岩岩性[J]. 特种油气藏, 2021 , 28(6) : 62 -69 . DOI: 10.3969/j.issn.1006-6535.2021.06.008

Abstract

To address the problems that it is difficult to classify igneous rock lithology in igneous rock reservoirs and the lithology identification accuracy is greatly affected by the number of slice identification samples,the correlation between different logging curves and igneous rock lithology was analyzed by random forest (RF) algorithm,and then igneous rock lithology was classified by the the K-nearest neighbor (KNN) algorithm according to the slice sample identification.The study results were applied to the Permian igneous rock formation in Western Sichuan,and the results showed that the correlation between logging curves and lithology was decreased in order of GR, R_t, DEN,CNL and AC.The igneous rock lithology was classified with the KNN algorithm, and the value of k was controlled by two factors: the number of classifications and the number of training samples.When there were less samples,the effect of the latter was greater than that of the former.When k was 3, the backcasting accuracy of KNN algorithm was 87.5% for 24 igneous rock training samples (5 types of lithology),and the testing accuracy was 92.5% for 14 igneous rock samples (5 types of lithology).In the classification of igneous rock lithology with comparison of charts,there was less man-made influence on the KNN algorithm and the parameter adjustment was simple.This study provides an important guide to the classification of igneous rock lithology with small samples.

Key words： igneous rock reservoir; lithology classification; slice identification; KNN; random forest

参考文献

[1] 吴煜宇,赖强,谢冰,等.四川盆地永探1井二叠系火山岩测井岩性识别[J].天然气勘探与开发,2019,42(1):21-27.
WU Yuyu,LAI Qiang,XIE Bing,et al.Logging-based lithologic identifying Permian volcanic rocks of Well Yongtan 1,Sichuan Basin[J].Natural Gas Exploration and Development,2019,42(1):21-27.
[2] 陈钢花,梁莎莎,王军,等.卷积神经网络在岩性识别中的应用[J].测井技术,2019,43(2):129-134.
CHEN Ganghua,LIANG Shasha,WANG Jun,et al.Application of convolutional neural network in lithology identification[J].Well Logging Technology,2019,43(2):129-134.
[3] 冯翠菊,王敬岩,冯庆付.利用测井资料识别火成岩岩性的方法[J].大庆石油学院学报,2004,28(4):9-11,109-110.
FENG Cuiju,WANG Jingyan,FENG Qingfu.Distinguishing igneous rock lithology by logging data[J].Journal of Daqing Petroleum Institute,2004,28(4):9-11,109-110.
[4] 吴煜宇,谢冰,伍丽红,等.四川盆地二叠系基性火山岩测井评价技术——以永探1井区火山岩为例[J].天然气工业,2019,39(2):37-45.
WU Yuyu,XIE Bing,WU Lihong,et al.Logging based lithology identification of Permian mafic volcanic rocks in the Sichuan Basin:a case study from the Well Yongtan 1[J].Natural Gas Industry,2019,39(2):37-45.
[5] 张丽华,张国斌,齐艳萍,等.准噶尔盆地西泉地区石炭系火山岩岩性测井识别[J].新疆石油地质,2017,38(4):427-431.
ZHANG Lihua,ZHANG Guobin,QI Yanping,et al.Lithology identification of carboniferous volcanic rock with logging data in Xiquan Area,Junggar Basin[J].Xinjiang Petroleum Geology,2017,38(4):427-431.
[6] 葛红旗.酸性火山岩岩性识别方法及应用[J].油气藏评价与开发,2015,5(5):11-16.
GE Hongqi.Lithologic identification method and application of acidic volcanic rocks[J].Reservoir Evaluation and Development,2015,5(5):11-16.
[7] 王满,薛林福,潘保芝.FMI图像纹理统计方法识别火成岩岩性[J].测井技术,2009,33(2):110-114.
WANG Man,XUE Linfu,PAN Baozhi.Lithology identification of igneous rock using FMI texture analysis[J].Well Logging Technology,2009,33(2):110-114.
[8] 金云智,高楚桥,高永德,等.用地层元素测井资料定量计算火成岩岩性组分[J].测井技术,2018,42(5):521-524.
JIN Yunzhi,GAO Chuqiao,GAO Yongde,et al.Quantitative calculation of igneous rocks lithology by using element logging data[J].Well Logging Technology,2018,42(5):521-524.
[9] 张莹,潘保芝.支持向量机与微电阻率成像测井识别火山岩岩性[J].物探与化探,2011,35(5):634-638,642.
ZHANG Ying,PAN Baozhi.The application of SVM and FMI to the lithologic identification of volcanic rocks[J].Geophysical and Geochemical Exploration,2011,35(5):634-638,642.
[10] 叶涛,韦阿娟,黄志,等.基于主成分分析法与Bayes判别法组合应用的火山岩岩性定量识别:以渤海海域中生界为例[J].吉林大学学报(地球科学版),2019,49(3):873-880.
YE Tao,WEI Ajuan,HUANG Zhi,et al.Quantitative identification of volcanic lithology based on comprehensive principal component analysis and Bayes discriminant method:a case study of Mesozoic in Bohai Bay[J].Journal of Jilin University(Earth Science Edition),2019,49(3):873-880.
[11] 王红菲,江玉龙,陆哲昆,等.辽河东部凹陷火成岩测井岩性识别方法与应用[J].世界地质,2016,35(2):510-516,525.
WANG Hongfei,JIANG Yulong,LU Zhekun,et al.Lithologic identification and application for igneous rocks in eastern depression of Liaohe oil field[J].Global Geology,2016,35(2):510-516,525.
[12] 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.
[13] 陈玉林,李戈理,杨智新,等.基于KNN算法识别合水地区长₇储层岩性岩相[J].测井技术,2020,44(2):182-185.
CHEN Yulin,LI Geli,YANG Zhixin,et al.Identification of Lithology and Lithofacies of Chang₇ Reservoir in Heshui Area by KNN algorithm[J].Logging Technology,2020,44(2):182-185.
[14] 纪磊,李菊花,肖佳林. 随机森林算法在页岩气田多段压裂改造中的应用[J].大庆石油地质与开发,2020,39(6):168-174.
JI Lei,LI Juhua,XIAO Jialin. Application of random forest algorithm in the multistage fracturing stimulation of shale gas field[J].Petroleum Geology & Oilfield Development in Daqing,2020,39(6):168-174.
[15] 康东雅,向芳,邹佐元,等.鄂尔多斯盆地上古生界砂岩岩石学特征及岩性差异[J].断块油气田,2019,26(3):299-303.
KANG Dongya,XIANG Fang,ZOU Zuoyuan,et al.Petrological characteristics and lithological differences of Upper Paleozoic sandstone of Ordos Basin[J].Fault-Block Oil & Gas Field,2019,26(3):299-303.
[16] 任涛,张鑫,孙文,等.基于粒子群算法的间歇采油机制优化[J].断块油气田,2020,27(4):541-544.
REN Tao,ZHANG Xin,SUN Wen,et al.Optimization of intermittent recovery mechanism based on particle swarm calculation[J].Fault-Block Oil & Gas Field,2020,27(4):541-544.
[17] 王安龙.基于常规测井资料综合评价延川南致密砂岩气层[J].油气藏评价与开发,2019,9(2):75-79.
Wang Anlong.Comprehensive evaluation of dense sandstone gas layer in southern Yanchuan Area based on conventional logging data[J].Reservoir Evaluation and Development,2019,9(2):75-79.
[18] 陈俊,李林致,张锡新,等.火成岩岩性岩相特征及时空展布规律:以准噶尔盆地红山嘴地区石炭系火成岩为例[J].东北石油大学学报,2019,43(2):97-108.
CHEN Jun,LI Linzhi,ZHANG Xixin,et al. Characteristics of lithologic facies and space time distribution of igneous rocks:a case study of Carboniferous igneous rocks in Hongshanzui Area,Junggar Basin[J].Journal of Northeast Petroleum University,2019,43(2):97-108.
[19] 袁述武,李想,史乐,等.克拉玛依油田六、七、九区石炭系内幕有利火山岩储层岩性分布预测[J].大庆石油地质与开发,2019,38(6):40-45.
YUAN Shuwu,LI Xiang,SHI Le,et al.Prediction of the lithology distribution of favorable volcanic reservoirs in the inside Carboniferous system in Block 6, 7 and 9 of Karamay Oilfield[J].Petroleum Geology & Oilfield Development in Daqing,2019,38(6):40-45.
[20] 王德英,于海波,王启明,等. 渤海海域湖盆萎缩期浅水三角洲岩性油气藏差异成藏模式[J]. 东北石油大学学报,2018,42(3):16-25.
WANG Deying,YU Haibo,WANG Qiming,et al. Differences of hydrocarbon accumulation models of extremely shallow water delta in lacustrine basin shrinking period,Bohai Sea[J].Journal of Northeast Petroleum University,2018,42(3):16-25.
[21] 刘金华,刘世丽,马洪涛,等.金湖凹陷墩塘-小关地区戴一段岩性油藏成藏规律[J].断块油气田,2019,26(4):435-438.
LIU Jinhua,LIU Shili,MA Hongtao,et al.Lithologic reservoir-forming rules of first member of Dainan Formation in Duntang-Xiaoguan Area,Jinhu Sag[J].Fault-Block Oil & Gas Field,2019,26(4):435-438.
[22] 杨勇,李亨,杨多,等.钻遇断层阵列侧向测井响应特性正演研究[J].油气藏评价与开发,2019,9(2):50-55.
YANG Yong,LI Heng,YANG Duo,et al.Forward simulation of response characteristics of the array lateral logging in drilling process of fault[J].Reservoir Evaluation and Development, 2019,9(2):50-55.
[23] 胡琴,李志强,任航.模糊正交法在弧形盘式齿破岩性能评价中的应用[J].断块油气田,2019,26(3):389-393.
HU Qin,LI Zhiqiang,REN Hang.Application of fuzzy orthogonalization to rock-breaking performance of arc disc teeth[J].Fault-Block Oil & Gas Field,2019,26(3):389-393.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献