基于机器学习的鄂尔多斯盆地陇东地区长7段岩相测井识别方法

doi:10.13809/j.cnki.cn32-1825/te.2023.04.015

摘要/Abstract

摘要：

岩相分析是储层评价的基础，受取心数量和成本的影响，针对未取心井利用测井资料开展岩相识别工作至关重要。根据岩心薄片鉴定结果，并结合成像测井资料将鄂尔多斯盆地陇东地区长7段岩相划分为6类。在岩心标定的基础上，对各类岩相的测井响应特征进行总结，建立该研究区基于常规测井曲线的岩相识别模式，结合机器学习算法开展岩相的自动识别。由于传统的分类算法受岩相样本不均衡的影响较大，对比多种不均衡数据分类算法在该地区的应用效果发现，集成学习Bagging算法通过组合多个基分类器，极大地改善了各类岩相的分类性能，并将该地区岩相的整体识别精度提升了20 %。据地区应用效果显示，单井识别精度可达84.33 %，具有较好的适用性。

关键词: 岩相, 测井响应特征, 非均衡数据集, 分类, 陇东地区长7段

Abstract:

Lithofacies analysis serves as the foundation for reservoir evaluation. However, due to the limited coring quantity and cost constraints, identifying lithofacies using logging data for uncored wells becomes crucial. In the Longdong area of the Ordos Basin, the lithofacies of the Chang-7 member have been classified into six types dependent on core identification results and imaging logging data. Based on core calibration, the logging response characteristics of different lithofacies were summarized, leading to the establishment of the lithofacies recognition mode using conventional logging curve. To achieve automatic lithofacies recognition in the study area, machine learning algorithms were employed. The traditional classification algorithms were affected significantly by the unbalanced sample. After comparing the application effects of different unbalanced data classification algorithm in the region, it’s found that bagging algorithm of ensemble learning notably improved the classification performance of all lithofacies by combining multiple classifiers. As a result, the overall lithofacies identification precision of this region has been improved by 20 %. According to the regional application results, the identification accuracy of single well can reach 84.33 %, demonstrating its practical applicability and effectiveness.

Key words: logging response characteristics, lithofacies, unbalanced data, classification, Chang-7 member in Longdong area

中图分类号:

TE122

谌丽,王才志,宁从前,刘英明,王浩. 基于机器学习的鄂尔多斯盆地陇东地区长7段岩相测井识别方法[J]. 油气藏评价与开发, 2023, 13(4): 525-536.

SHEN Li,WANG Caizhi,NING Congqian,LIU Yingming,WANG Hao. Well-log lithofacies classification based on machine learning for Chang-7 member in Longdong area of Ordos Basin[J]. Petroleum Reservoir Evaluation and Development, 2023, 13(4): 525-536.

图/表 16

图1

图2

图3

图4

图5

表1

图6

表2

图7

图8

图9

图10

图11

图12

表3

图13

参考文献 34

[1]	付锁堂, 金之钧, 付金华, 等. 鄂尔多斯盆地延长组7段从致密油到页岩油认识的转变及勘探开发意义[J]. 石油学报, 2021, 42(5): 561-569. doi: 10.7623/syxb202105001
	FU Suotang, JIN Zhijun, FU Jinhua, et al. Transformation of understanding from tight oil to shale oil in the Member 7 of Yanchang Formation in Ordos Basin and its significance of exploration and development[J]. Acta Petrolei Sinica, 2021, 42(5): 561-569. doi: 10.7623/syxb202105001
[2]	HALL B. Facies classification using machine learning[J]. The Leading Edge, 2016, 35(10): 906-909. doi: 10.1190/tle35100906.1
[3]	BESTAGINI P, LIPARI V, TUBARO S. A machine learning approach to facies classification using well logs[C]// Paper SEG-2017-17729805 presented at the 2017 SEG International Exposition and Annual Meeting, Houston, Texas, September 2017.
[4]	NISHITSUJI Y, EXLEY R. Elastic impedance based facies classification using support vector machine and deep learning[J]. Geophysical Prospecting, 2019, 67(4): 1040-1054. doi: 10.1111/gpr.2019.67.issue-4
[5]	石小松, 程国建. 用自组织特征映射神经网络识别岩相[J]. 电脑知识与技术, 2008, 4(26): 1764-1766.
	SHI Xiaosong, CHENG Guojian. The logging lithological identification by using self-organizing feature map neural networks[J]. Computer Knowledge and Technology, 2008, 4(26): 1764-1766.
[6]	薛林福, 潘保芝. 用自组织神经网络自动识别岩相[J]. 长春科技大学学报, 1999, 29(2): 144-147.
	XUE Linfu, PAN Baozhi. Identify lithofacies automatically using self-organizing neural network[J]. Journal of Changchun University of Science and Technology, 1999, 29(2): 144-147.
[7]	郭荣坤, 王忠东. ANN测井相分析方法研究[J]. 地球物理学进展, 1996, 11(2): 53-65
	GUO Rongkun, WANG Zhongdong. Analysis of well logging facies by ANN technique[J]. Progress in Geophysics, 1996, 11(2): 53-65.
[8]	付金华, 李士祥, 牛小兵, 等. 鄂尔多斯盆地三叠系长7段页岩油地质特征与勘探实践[J]. 石油勘探与开发, 2020, 47(5): 870-883. doi: 10.11698/PED.2020.05.03
	FU Jinhua, LI Shixiang, NIU Xiaobing, et al. Geological characteristics and exploration of shale oil in Chang 7 Member of Triassic Yanchang Formation, Ordos Basin, NW China[J]. Petroleum Exploration and Development, 2020, 47(5): 870-883. doi: 10.11698/PED.2020.05.03
[9]	张才利, 刘新社, 杨亚娟, 等. 鄂尔多斯盆地长庆油田油气勘探历程与启示[J]. 新疆石油地质, 2021, 42(3): 253-263.
	ZHANG Caili, LIU Xinshe, YANG Yajuan, et al. Petroleum exploration history and enlightenment of Changqing Oilfield in Ordos Basin[J]. Xinjiang Petroleum Geology, 2021, 42(3): 253-263.
[10]	付锁堂, 姚泾利, 李士祥, 等. 鄂尔多斯盆地中生界延长组陆相页岩油富集特征与资源潜力[J]. 石油实验地质, 2020, 42(5): 698-710.
	FU Suotang, YAO Jingli, LI Shixiang, et al. Enrichment characteristics and resource potential of continental shale oil of Mesozoic Yanchang formation, Ordos Basin[J]. Petroleum Geology & Experiment, 2020, 42(5): 698-710.
[11]	林世杭. 基于层次化随机森林的多标签分类算法研究[D]. 广州: 华南理工大学, 2017.
	LIN Shihang. Multi-label classification algorithm based on hierarchical random forest[D]. Guangzhou: South China University of Technology, 2017.
[12]	陶新民, 郝思媛, 张冬雪, 等. 不均衡数据分类算法的综述[J]. 重庆邮电大学学报(自然科学版), 2013, 25(1): 101-110.
	TAO Xinmin, HAO Siyuan, ZHANG Dongxue, et al. Overview of classification algorithms for unbalanced data[J], Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2013, 25(1): 101-110.
[13]	崔鑫, 徐华, 朱亮, 等. 面向不均衡数据的多分类集成算法[J]. 计算机工程与应用, 2022, 58(2): 176-183. doi: 10.3778/j.issn.1002-8331.2008-0058
	CUI Xin, XU Hua, ZHU Liang, et al. Multi-classification ensemble algorithm for imbalanced data[J]. Computer Engineering and Applications, 2022, 58(2): 176-183. doi: 10.3778/j.issn.1002-8331.2008-0058
[14]	马陇飞, 萧汉敏, 陶敬伟, 等. 基于深度学习岩性分类的研究与应用[J]. 科学技术与工程, 2022, 22(7): 2609-2617.
	MA Longfei, XIAO Hanmin, TAO Jingwei, et al. Research and application of lithology classification based on deep learning[J]. Science Technology and Engineering, 2022, 22(7): 2609-2617.
[15]	马陇飞, 萧汉敏, 陶敬伟, 等. 基于梯度提升决策树算法的岩性智能分类方法[J]. 油气地质与采收率, 2022, 29(1): 21-29.
	MA Longfei, XIAO Hanmin, TAO Jingwei, et al. Intelligent lithology classification method based on GBDT algorithm[J]. Petroleum Geology and Recovery Efficiency, 2022, 29(1): 21-29.
[16]	王民, 杨金路, 王鑫, 李进步, 等. 基于随机森林算法的泥页岩岩相测井识别[J]. 地球科学, 2023, 48(1): 130-142.
	WANG Min, YANG Jinlu, WANG Xin, et al. Identification of shale lithofacies by well logs based on random forest algorithm[J]. Earth Science, 2023, 48(1): 130-142.
[17]	李昌, 沈安江, 常少英, 等. 机器学习法在碳酸盐岩岩相测井识别中应用及对比——以四川盆地MX地区龙王庙组地层为例[J]. 油气藏评价与开发, 2021, 11(4): 586-596.
	LI Chang, SHEN Anjiang, CHANG Shaoying, et al. Application and contrast of machine learning in carbonate lithofacies log identification: A case study of Longwangmiao Formation of MX area in Sichuan Basin[J]. Petroleum Reservoir Evaluation and Development, 2021, 11(4): 586-596.
[18]	杨静, 陈云天, 蒋春碧. 测井曲线生成问题的机器学习建模范式——以长宁威远地区页岩井为例[J]. 中国海上油气, 2021, 33(1): 76-84.
	YANG Jing, CHEN Yuntian, JIANG Chunbi. Machine learning modeling paradigm for log curve generation problems: Taking shale gas wells in Changning-Weiyuan area as examples[J]. China Offshore Oil and Gas, 2021, 33(1): 76-84.
[19]	杨明任, 申辉林, 曲萨, 等. AdaBoost算法在致密砂岩水淹层识别中的应用[J]. 中国海上油气, 2021, 33(4): 62-69.
	YANG Mingren, SHEN Huilin, QU Sa, et al. Application of AdaBoost algorithm in recognition of water flooded tight sandstone layer[J]. China Offshore Oil and Gas, 2021, 33(4): 62-69.
[20]	刘龙龙, 孙中强, 张金亮, 等. 丽水凹陷古新统储层成岩相测井识别与预测[J]. 中国海上油气, 2021, 33(1): 64-75.
	LIU Longlong, SUN Zhongqiang, ZHANG Jinliang, et al. Logging identification and prediction of Paleocene reservoir diagenetic facies in Lishui sag[J]. China Offshore Oil and Gas, 2021, 33(1): 64-75.
[21]	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]. Well Logging Technology, 2020, 44(2): 182-185.
[22]	李文昊. 基于统计学习方法的储层岩相分类研究[D]. 成都: 电子科技大学, 2018.
	LI Wenhao. Research on reservoir lithofacies classification based on statistical learning method[D]. Chengdu: University of Electronic Science and Technology of China, 2018.
[23]	吕红燕, 冯倩. 随机森林算法研究综述[J]. 河北省科学院学报, 2019, 36(3): 37-41.
	LYU Hongyan, FENG Qian. A review of random forests algorithm[J]. Journal of Hebei Academy of Sciences, 2019, 36(3): 37-41.
[24]	潘主强, 张林, 张磊, 等. 中医临床不均衡数据疾病分类方法研究[J]. 智能系统学报, 2017, 12(6): 848-856.
	PAN Zhuqiang, ZHANG Lin, ZHANG Lei, et al. Research on classification of diseases of clinical imbalanced data in traditional Chinese medicine[J]. CAAI transactions on intelligent systems, 2017, 12(6): 848-856.
[25]	徐丽丽. 面向不均衡数据集的分类算法研究[D]. 大连: 辽宁师范大学, 2016.
	XU Lili. Research on classification algorithm of imbalanced data sets[D]. Dalian: Liaoning Normal University, 2016.
[26]	谷琼. 面向非均衡数据集的机器学习及在地学数据处理中的应用[D]. 武汉: 中国地质大学, 2009.
	GU Qiong. Research of machine learning on imbalanced data sets and its application in geosciences data processing[D]. Wuhan: China University of Geosciences, 2009.
[27]	SALEH W B, SAGAR T. Comparative analysis of machine learning classifiers in an imbalanced facies distributed dataset from a libyan carbonate reservoir[C]// Paper OMC-2021-40 presented at the OMC Med Energy Conference and Exhibition, Ravenna, Italy, September 2021.
[28]	GUARIDO M, EMERY D J, MACQUET M, et al. Pitfalls and insights from a machine learning contest on log facies classification[C]// Paper SEG-2021-3580872 presented at the SEG/AAPG/SEPM First International Meeting for Applied Geoscience & Energy, Denver, Colorado, USA and online, September 2021.
[29]	HU C S, SUN B Q. Multitask learning for petrophysical attribute prediction using convolutional neural network and imbalance dataset[C]// Paper SEG-2020-W13-03 presented at the SEG International Exposition and Annual Meeting, Virtual, October 2020.
[30]	HALL B. Facies classification using machine learning[J]. The Leading Edge, 2016, 35: 906-909. doi: 10.1190/tle35100906.1
[31]	GUYAGULER B, HORNE R N, ROGERS L. Optimization of well placement in a Gulf of Mexico waterflooding project[J]. SPE Reservoir Evaluation & Engineering, 2002, 5(3): 229-236.
[32]	EMELYANOVA I, PEYAUD J B, DANCE T, et al. Detecting specific facies in well-log data sets using knowledge-driven hierarchical clustering[J]. Petrophysics, 2020, 61(4): 383-400.
[33]	唐伟, 周志华. 基于Bagging的选择性聚类集成[J]. 软件学报, 2005, 16(4): 496-502. doi: 10.1360/jos160496
	TANG Wei, ZHOU Zhihua. Bagging-based selective cluster ensemble[J]. Journal of Software, 2005, 16(4): 496-502. doi: 10.1360/jos160496
[34]	车翔玖, 于英杰, 刘全乐. 增强bagging集成学习及多目标检测算法[J]. 吉林大学学报(工学版), 2022, 52(12): 2916-2923.
	CHE Xiangjiu, YU Yingjie, LIU Quanle. Enhanced bagging ensemble learning and multi-target detection algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(12): 2916-2923.

岩相类型	样本数/个	岩相类型	样本数/个
均质砂岩	1 848	粉砂质泥岩	6 634
非均质砂岩	6 331	黑色页岩	2 585
暗色泥岩	3 369	凝灰岩	487

欠采样方法	岩相样本数/个
欠采样方法	均质砂岩	非均质砂岩	暗色泥岩	粉砂质泥岩	黑色页岩	凝灰岩
不采样	1 290	4 429	2 322	4 657	1 843	336
随机欠采样	336	336	336	336	336	336
OSS	1 157	3 640	2 100	4 393	860	336
ENN	786	2 971	1 219	3 134	1 564	336
NCR	1 021	3 795	1 828	4 144	1 723	336
随机过采样	4 657	4 657	4 657	4 657	4 657	4 657
SMOTE	4 657	4 657	4 657	4 657	4 657	4 657
ADASYN	1 290	4 429	2 322	4 657	1 843	4 683
Borderline- SMOTE	4 657	4 657	4 657	4 657	4 657	4 657

序号	井名	岩心标定/个	模型识别/个	准确率/%
1	L34	877	723	82.44
2	L43	828	669	81.74
3	L49	1 029	832	80.86
4	L55	836	669	81.04
5	L97	1 294	1 071	82.79
6	T38	957	767	80.19
7	N196	855	721	84.33
8	M139	861	708	82.22
9	M160	935	749	83.15
10	L303	880	725	82.44