基于图论聚类和最小临近算法的岩性识别方法——以四川盆地西部雷口坡组碳酸盐岩储层为例

doi:10.11743/ogg20200420

摘要/Abstract

摘要：

碳酸盐岩具有非均质性强、岩性变化快和岩石类型复杂的特征，岩性精细识别难度大，严重制约了储层参数的计算及后续油气开发。以四川盆地西部雷口坡组碳酸盐岩储层为例，结合岩心和薄片等分析测试资料将储层发育的岩性分为8类：藻粘结白云岩、粉晶白云岩、泥晶白云岩、灰质白云岩、白云质灰岩、灰岩、膏质白云岩和石膏，明确了不同岩性的测井响应特征。采用机器学习的思想，将已知岩性定名样本作为训练数据，利用图论聚类分析方法建立岩性识别训练模型，在此基础上结合最小临近算法对未取心井岩性进行预测，实现了不同岩性的精细识别。区块应用结果表明：该方法岩性识别整体符合率高达91.3%，有效提高了岩性识别精度。

关键词: 测井响应, 机器学习, 图论聚类, 最小临近算法, 盲井预测, 岩性识别, 碳酸盐岩, 四川盆地西部

Abstract:

Carbonate rocks have the characteristics of strong heterogeneity, changing lithology and various rock types, which make it difficult to recognize their fine lithologic features and seriously restrict the calculation of reservoir parameters as well as subsequent oil/gas development. The carbonate reservoirs in the Leikoupo Formation in western Sichuan Basin were studied to deal with the problem. Core and thin slice observation and other analysis results revealed eight distinctive lithologic facies in the reservoirs: the algal bonded dolomite, crystal powder dolomite, dolomicrite, calcite dolomite, dolomitic limestone, limestone, gypsum dolomite and gypsum. Their log responses were also identified. In addition, machine learning was combined with multi-resolution graph-based clustering to establish a lithology identification training model by using the known and named lithologic samples as training data. Subsequently, the lithology of reservoirs in other wells was predicted with the K-Nearest Neighbor, thus realizing a fine identification of different lithologic facies. Field application of the method shows a 91.3% of overall coincidence rate of lithology recognition, indicating an improved accuracy in lithology identification.

Key words: log response, machine learning, graphic clustering, K-Nearest Neighbor, unknown well prediction, lithology identification, carbonate, western Sichuan Basin

中图分类号:

TE135.1

孔强夫,杨才,李浩,等. 基于图论聚类和最小临近算法的岩性识别方法——以四川盆地西部雷口坡组碳酸盐岩储层为例[J]. 石油与天然气地质, 2020, 41(4): 884-890. doi: 10.11743/ogg20200420 Qiangfu Kong,Cai Yang,Hao Li,et al. A lithology recognition method based on multi-resolution graph-based clustering and K-Nearest Neighbor:A case study from the Leikoupo Formation carbonate reservoirs in western Sichuan Basin[J]. Oil & Gas Geology, 2020, 41(4): 884-890. doi: 10.11743/ogg20200420

图/表 8

图1

图2

图3

图4

图5

表1

图6

图7

参考文献 23

1	吴世祥, 李宏涛, 龙胜祥, 等. 川西雷口坡组碳酸盐岩储层特征及成岩作用[J]. 石油与天然气地质, 2011, 32 (4): 542- 550.
	Wu Shixiang , Li Hongtao , Long Shengxiang , et al. A study on characteristics and diagenesis of carbonate reservoirs in the Middle Triassic Leikoupo Formation in western Sichuan Depression[J]. Oil & Gas Geology, 2011, 32 (4): 542- 550.
2	高恒逸, 邓美洲, 李勇, 等. 川西彭州地区中三叠统雷口坡组四段储层特征及成岩作用[J]. 海相油气地质, 2018, 23 (1): 37- 46. doi: 10.3969/j.issn.1672-9854.2018.01.005
	Gao Hengyi , Deng Mei , Li Yong , et al. Diagenesis and reservoir chara-cteristics in the Middle Triassic Lei-4 Member of Leikoupo Formation in Pengzhou area of western Sichuan Basin[J]. Marine Origin Petroleum Geology, 2018, 23 (1): 37- 46. doi: 10.3969/j.issn.1672-9854.2018.01.005
3	王琼仙, 宋晓波, 王东, 等. 川西龙门山前雷口坡组四段储层特征及形成机理[J]. 石油实验地质, 2017, 39 (4): 491- 497.
	Wang Qiongxian , Song Xiaobo , Wang Dong , et al. Reservoir characteristics and formation mechanism of the 4th member of the Leikoupo Formation in Longmen mountain front[J]. Petroleum Geology & Experiment, 2017, 39 (4): 491- 497.
4	周凌方, 钱一雄, 宋晓波, 等. 四川盆地西部彭州气田中三叠统雷口坡组四段上亚段白云岩孔隙表征、分布及成因[J]. 石油与天然气地质, 2020, 41 (1): 177- 188.
	Zhou Lingfang , Qian Yixiong , Song Xiaobo , et al. Characteristics, distribution and origin of dolomite reservoir in the upper Lei 4 member of the Middle Triassic, Pengzhou gas field, western Sichuan Basin[J]. Petroleum & Gas Geology, 2020, 541 (1): 177- 188.
5	陈昱林, 曾焱, 段永明, 等. 川西龙门山前雷口坡组四段白云岩储层孔隙结构特征及储层分类[J]. 石油实验地质, 2018, 40 (5): 621- 631.
	Chen Yulin , Zeng Yan , Duan Yongming , et al. Pore structure characteristics and reservoir classification of dolomite reservoirs in fourth member of Leikoupo Formation, Longmen Mountain front, western Sichuan Basin[J]. Petroleum Geology & Experiment, 2018, 40 (5): 621- 631.
6	赵向原, 胡向阳, 肖开华, 等. 川西彭州地区雷口坡组碳酸盐岩储层裂缝特征及主控因素[J]. 石油与天然气地质, 2018, 39 (1): 30- 39.
	Zhao Xiangyuan , Hu Xiangyang , Xiao Kaihua , et al. Characteristics and major control factors of natural fractures in carbonate reservoirs of Leikoupo Formation in Pengzhou area, western Sichuan Basin[J]. Oil & Gas Geology, 2018, 39 (1): 30- 39.
7	王晓畅, 张军, 李军, 等. 基于交会图决策树的缝洞体类型常规测井识别方法——以塔河油田奥陶系为例[J]. 石油与天然气地质, 2017, 38 (4): 805- 812.
	Wang Xiaochang , Zhang Jun , Li Jun , et al. Conventional logging identification of fracture-vug complex types data based on crossplots-decision tree:A case study from the Ordovician in Tahe oilfield, Tarim Basin[J]. Oil & Gas Geology, 2017, 38 (4): 805- 812.
8	Chang S K, Juprasert S, Jusbasche M.An evaluation of a rhyolite-basalt-volcanic ash sequence from well logs[C].SPWLA 20th Annual Logging Symposium, Tulsa, Oklahorma, 1979: SPWLA-1979-TT.
9	Khatchikian A.Log evaluation of oil-bearing igneous rocks[C].SPWLA 23th Annual Logging Symposium, Corpus Christ, Texas, 1982: SPWLA-1982-AA.
10	刘爱疆, 左烈, 李景景, 等. 主成分分析法在碳酸盐岩岩性识别中的应用——以地区寒武系碳酸盐岩储层为例[J]. 石油与天然气地质, 2013, 34 (2): 192- 196.
	Liu Aijiang , Zuo lie , Li Jingjing , et al. Application of principal component analysis in carbonate lithology identification:A case study of the Cambrian carbonate reservoir in YH field[J]. Oil & Gas Geology, 2013, 34 (2): 192- 196.
11	潘保芝, 闫桂京, 吴海波. 对应分析确定松辽盆地北部深层火成岩岩性[J]. 大庆石油地质与开发, 2003, 22 (1): 7- 9. doi: 10.3969/j.issn.1000-3754.2003.01.003
	Pan Baozhi , Yan Guijing , Wu Haibo . Determining lithology of igneous rocks in deep northern Songliao Basin using correspondence analysis[J]. Petroleum Geology & Oilfield Development in Daqing, 2003, 22 (1): 7- 9. doi: 10.3969/j.issn.1000-3754.2003.01.003
12	张翔, 王智, 罗菊兰, 等. 基于逐步判别与支持向量机方法的沉积微相定量识别[J]. 测井技术, 2010, 34 (4): 365- 369. doi: 10.3969/j.issn.1004-1338.2010.04.013
	Zhang Xiang , Wang Zhi , Luo Julan , et al. Quantitative identification of microfacies based on stepwise discrimination and support vector machine[J]. Well Logging Technology, 2010, 34 (4): 365- 369. doi: 10.3969/j.issn.1004-1338.2010.04.013
13	张治国, 杨毅恒, 夏立显. 自组织特征映射神经网络在测井岩性识别中的应用[J]. 地球物理学进展, 2005, 20 (2): 332- 336. doi: 10.3969/j.issn.1004-2903.2005.02.013
	Zhang Zhiguo , Yang Yiheng , Xia Lixian . The application of self-organizing feature map neural network to logging lithological identification[J]. Progress in Geophysics, 2005, 20 (2): 332- 336. doi: 10.3969/j.issn.1004-2903.2005.02.013
14	刘传平, 郑建东, 杨景强. 徐深气田深层火山岩测井岩性识别方法[J]. 石油学报, 2006, 27 (B12): 62- 65.
	Liu Chuanping , Zheng Jiandong , Yang Jingqiang . Lithology identification of well iogging for deep volcanic reservoir in Xushen gas field[J]. Acta Petrolei Sinica, 2006, 27 (B12): 62- 65.
15	王硕儒, 范德江, 汪丙柱. 岩相识别的神经网络计算[J]. 沉积学报, 1996, 14 (4): 154- 160.
	Wang Shuru , Fan Dejiang , Wang Bingzhu . Facies recognition using the neural networks[J]. Acta Sedimentologica Sinica, 1996, 14 (4): 154- 160.
16	韩玉娇, 袁超, 范宜仁, 等. 基于经验模态分解和能量熵判别的火成岩岩性识别方法——以春风油田石炭系火成岩储层为例[J]. 石油与天然气地质, 2018, 39 (4): 759- 765.
	Han Yujiao , Yuan Chao , Fan Yiren , et al. Identification of igneous reservoir lithology based on empirical mode decomposition and energy entropy classification:A case study of Carboniferous igneous reservoir in Chunfeng oilfield[J]. Oil & Gas Geology, 2018, 39 (4): 759- 765.
17	李昌, 乔占峰, 邓兴梁, 等. 视岩石结构数技术在测井识别碳酸盐岩岩相中的应用[J]. 油气地球物理, 2017, 15 (1): 29- 35.
	Li Chang , Qiao Zhanfeng , Deng Xingliang , et al. Application of apparent rock structure number technique in identifying carbonate lithofacies by well logging[J]. Geophysics of Oil and Gas, 2017, 15 (1): 29- 35.
18	Stowe L, Hock M.Facies analysis and diagenesis from well logs in the Zechstein carbonates of northern Germany[C].SPWLA 29th Annual Logging Symposium, San Antonio, Texas, 1988: SPWLA-1988-HH.
19	Tanwi B, Kuwait, Robert D, et al.Automated facies estimation from integration of core, petrophysical logs and borehole images[C].American Association of Petroleum Geologists Annual Meeting, Houston, 2002: 1-7.
20	Pabakhsh M , Ahmadi K , Riahi M A , et al. Prediction of PEF and LITH logs using MRGC approach[J]. Life Science Journal, 2012, 9 (4): 974- 982.
21	吴进波. MRGC方法在储层分类及渗透率精细评价中的应用[J]. 海洋石油, 2017, 37 (1): 49- 53. doi: 10.3969/j.issn.1008-2336.2017.01.049
	Wu Jinbo . Application of reservoir classification and permeability elaborate evaluation with MRGC method[J]. Offshore Oil, 2017, 37 (1): 49- 53. doi: 10.3969/j.issn.1008-2336.2017.01.049
22	李艳华, 王红涛, 王鸣川, 等. 基于PCA和KNN的碳酸盐岩沉积相测井自动识别[J]. 测井技术, 2017, 41 (1): 57- 63.
	Li Yanhua , Wang Hongtao , Wang Mingchuan , et al. Automatic identification of carbonate sedimentary facies logging based on PCA and KNNusing Logs[J]. Well Logging Technology, 2017, 41 (1): 57- 63.
23	田雨, 徐洪, 张兴阳, 等. 基于图论多分辨率聚类分析的测井岩相识别研究——以阿姆河盆地台内滩气田为例[J]. 应用地球物理:英文版, 2016, (4): 598- 607.
	Tian Yu , Xu Hong , Zhang Xingyang , et al. Multi-resolution graph-based clustering analysis for lithofacies identification from well log data:Case study of intraplatform bank gas fields, Amu Darya Basin[J]. Applied Geophysics, 2016, (4): 598- 607.

井名	顶深/m	测井岩性	薄片定名	是否符合
彭州1井	5 820.65	粉晶白云岩	粉晶白云岩	是
彭州1井	5 822.77	灰质白云岩	灰质白云岩	是
彭州1井	5 824.50	灰质白云岩	白云质灰岩	否
彭州103井	5 941.00	灰岩	灰岩	是
彭州103井	5 949.00	灰岩	灰岩	是
彭州103井	6 023.56	泥晶白云岩	灰质白云岩	否
彭州103井	6 043.65	粉晶白云岩	粉晶白云岩	是
彭州115井	6 331.36	白云质灰岩	白云质灰岩	是
彭州115井	6 371.00	泥晶白云岩	泥晶白云岩	是
彭州115井	6 380.00	灰岩	白云质灰岩	否
羊深1井	6 202.80	藻粘结白云岩	藻粘结白云岩	是
羊深1井	6 202.90	藻粘结白云岩	藻粘结白云岩	是
鸭深1井	5 771.50	粉晶白云岩	粉晶白云岩	是
鸭深1井	5 771.60	粉晶白云岩	粉晶白云岩	是
白云岩类符合率		94.6%	总体符合率	91.3%
灰岩类符合率		87.2%	总体符合率	91.3%

[1]	丁文龙, 李云涛, 韩俊, 黄诚, 王来源, 孟庆修. 碳酸盐岩储层高精度构造应力场模拟与裂缝多参数分布预测方法及其应用[J]. 石油与天然气地质, 2024, 45(3): 827-851.
[2]	杨德彬, 鲁新便, 鲍典, 曹飞, 汪彦, 王明, 谢润成. 塔里木盆地北部奥陶系海相碳酸盐岩断溶体油藏成因类型及特征再认识[J]. 石油与天然气地质, 2024, 45(2): 357-366.
[3]	张赫驿, 杨帅, 张玺华, 彭瀚霖, 李乾, 陈聪, 高兆龙, 陈安清. 川东地区中二叠统茅口组沉积微相与环境演变[J]. 石油与天然气地质, 2024, 45(2): 457-470.
[4]	江同文, 邓兴梁, 曹鹏, 常少英. 塔里木盆地富满断控破碎体油藏储集类型特征与注水替油效果[J]. 石油与天然气地质, 2024, 45(2): 542-552.
[5]	屈海洲, 郭新宇, 徐伟, 李文皓, 唐松, 邓雅霓, 何仕鹏, 张云峰, 张兴宇. 碳酸盐岩微孔隙的分类、成因及对岩石物理性质的影响[J]. 石油与天然气地质, 2023, 44(5): 1102-1117.
[6]	史今雄, 赵向原, 潘仁芳, 曾联波, 朱正平. 川中地区震旦系灯影组碳酸盐岩天然裂缝特征及其对气井产能影响[J]. 石油与天然气地质, 2023, 44(2): 393-405.
[7]	邹才能, 谢增业, 李剑, 张璐, 杨春龙, 崔会英, 王晓波, 郭泽清, 潘松圻. 典型碳酸盐岩大气田规模聚集差异性及其主控因素[J]. 石油与天然气地质, 2023, 44(1): 1-15.
[8]	张涛, 张亚雄, 金晓辉, 周雁, 张军涛, 谷宁, 张威, 王濡岳, 鲁锴. 鄂尔多斯盆地奥陶系马家沟组碳酸盐岩-蒸发岩层系层序地层模式及其对源-储的控制作用[J]. 石油与天然气地质, 2023, 44(1): 110-124.
[9]	刘建章, 蔡忠贤, 滕长宇, 张恒, 陈诚. 塔里木盆地顺北地区克拉通内走滑断裂带中-下奥陶统储集体方解石脉形成及其与油气充注耦合关系[J]. 石油与天然气地质, 2023, 44(1): 125-137.
[10]	何治亮, 赵向原, 张文彪, 吕心瑞, 朱东亚, 赵峦啸, 胡松, 郑文波, 刘彦锋, 丁茜, 段太忠, 胡向阳, 孙建芳, 耿建华. 深层-超深层碳酸盐岩储层精细地质建模技术进展与攻关方向[J]. 石油与天然气地质, 2023, 44(1): 16-33.
[11]	丁茜, 王静彬, 杨磊磊, 朱东亚, 江文滨, 何治亮. 基于模拟实验探讨断裂-流体-岩石体系中的矿物溶解-沉淀过程[J]. 石油与天然气地质, 2023, 44(1): 164-177.
[12]	李剑, 杨春龙, 谢武仁, 芮宇润, 王晓波, 张璐, 谢增业, 郭泽清. 四川盆地安岳气田震旦系台缘带和台内地区天然气成藏差异性及勘探领域[J]. 石油与天然气地质, 2023, 44(1): 34-45.
[13]	钱一雄, 武恒志, 周凌方, 董少峰, 王琼仙, 宋晓波, 邓美洲, 李勇. 深埋条件下微生物碳酸盐岩成岩作用与孔隙演化——以四川盆地西部中三叠统雷口坡组为例[J]. 石油与天然气地质, 2023, 44(1): 55-74.
[14]	韩月卿, 张军涛, 何治亮, 金振奎, 韩文彪, 高平, 郝运轻, 孙炜, 武重阳. 川西中二叠统栖霞组白云岩特征与成因[J]. 石油与天然气地质, 2023, 44(1): 75-88.
[15]	吕心瑞, 邬兴威, 孙建芳, 夏东领, 李彦普, 丁炎志, 王斌. 深层碳酸盐岩储层溶洞垮塌物理模拟及分布预测[J]. 石油与天然气地质, 2022, 43(6): 1505-1514.