基于改进型随机森林算法的页岩岩性识别——以准噶尔盆地芦草沟组为例

doi:10.7657/XJPG20240512

摘要/Abstract

摘要：

在储集层岩性识别的应用中，特别是对页岩等非均质性较强的非常规储集层的岩性识别，机器学习算法的高效性、准确性和有效信息整合能力已经得到了充分验证。考虑到岩性识别的特征参数优选问题，优选自然伽马、T₂几何平均值、结构指数、骨架密度指数、密度和深侧向电阻率，采用结合递归特征消除的随机森林算法，对准噶尔盆地中二叠统芦草沟组页岩储集层的主要岩性进行识别；利用传统的随机森林算法和支持向量机法，对同一套资料进行岩性预测，并与岩石薄片鉴定结果对比。结合递归特征消除的随机森林算法只需选择一半的测井参数，便能够达到更好的效果，而且通过优选特征参数，缩短了算法的运行时间。因此，结合递归特征消除的随机森林算法能够实现测井特征参数的优选，提高页岩岩性识别的准确率，缩短运行时间，为复杂岩性识别和多参数选择提供了新的思路。

关键词: 随机森林算法, 递归特征消除, 特征选择, 中二叠统, 芦草沟组, 页岩储集层, 岩性识别

Abstract:

In the application of reservoir lithology identification, the efficiency, accuracy and effective information integration ability of machine learning algorithm have been fully verified, especially in unconventional reservoirs with strong heterogeneity such as shale. Based on the optimal selection of parameters such as natural gamma, T₂ geometric mean, structural index, skeleton density index, density, and deep lateral resistivity, and using a random forest algorithm combined with recursive feature elimination (RF-RFE), major lithologies of the shale reservoirs in the Middle Permian Lucaogou formation in the Junggar basin were identified. Lithology prediction was conducted on the same dataset using conventional RF and support vector machine (SVM) algorithms, and the results were compared with those obtained from thin-section identifications. It is found that RF-RFE yields better results with only half of the logging parameters, and the parameters defined by optimal selection help reduce the algorithm’s running time. Thus, the use of RF-RFE algorithm can realize optimal selection of characteristic logging parameters, more accurate identification of shale lithology, and reduction of running time. The algorithm provides a new approach for complex lithology identification and multi-parameter selection.

Key words: random forest algorithm, recursive feature elimination, optimal selection, Middle Permian, Lucaogou formation, shale reservoir, lithology identification

中图分类号:

TE122.221

秦志军, 操应长, 冯程. 基于改进型随机森林算法的页岩岩性识别——以准噶尔盆地芦草沟组为例[J]. 新疆石油地质, 2024, 45(5): 595-603.

QIN Zhijun, CAO Yingchang, FENG Cheng. Shale Lithology Identification Based on Improved Random Forest Algorithm：A Case of Lucaogou Formation in Junggar Basin[J]. Xinjiang Petroleum Geology, 2024, 45(5): 595-603.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

参考文献 28

[1]	李宁, 徐彬森, 武宏亮, 等. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 2021, 42(4):508-522. doi: 10.7623/syxb202104008
	LI Ning, XU Binsen, WU Hongliang, et al. Application status and prospects of artificial intelligence in well logging and formation evaluation[J]. Acta Petrolei Sinica, 2021, 42(4):508-522. doi: 10.7623/syxb202104008
[2]	申辉林, 方鹏, 刘美杰. 用测井资料自动识别低孔低渗储集层岩性:以泌阳凹陷安棚古近系为例[J]. 新疆石油地质, 2010, 31(6):644-646.
	SHEN Huilin, FANG Peng, LIU Meijie. Using well log data to automatically identify lithology of reservoir with low porosity and low permeability:An example from Anpeng Paleogene in Biyang sag[J]. Xinjiang Petroleum Geology, 2010, 31(6):644-646.
[3]	WANG Guochang, JU Yiwen, HUANG Cheng, et al. Longmaxi-Wufeng shale lithofacies identification and 3-D modeling in the northern Fuling gas field,Sichuan basin[J]. Journal of Natural Gas Science and Engineering, 2017, 47:59-72.
[4]	FORD D, KELLY M, ANONYMOUS. Using neural networks to predict lithology from well logs[J]. SEG Annual Meeting Expanded Technical Program Abstracts with Biographies, 2001, 71:666-667.
[5]	刘跃杰, 刘书强, 马强, 等. BP神经网络法在三塘湖盆地芦草沟组页岩岩相识别中的应用[J]. 岩性油气藏, 2019, 31(4):101-111.
	LIU Yuejie, LIU Shuqiang, MA Qiang, et al. Application of BP neutral network method to identification of shale lithofacies of Lucaogou formation in Santanghu basin[J]. Lithologic Reservoirs, 2019, 31(4):101-111.
[6]	AL-ANAZI A, GATES I D. On the capability of support vector machines to classify lithology from well logs[J]. Natural Resources Research, 2010, 19(2):125-139.
[7]	周新锐, 王喜鑫, 李少华, 等. 陆相混积型页岩储集层孔隙结构特征及其控制因素[J]. 新疆石油地质, 2023, 44(4):411-420.
	ZHOU Xinrui, WANG Xixin, LI Shaohua, et al. Pore structure characteristics and controlling factors of continental mixed shale reservoirs[J]. Xinjiang Petroleum Geology, 2023, 44(4):411-420.
[8]	BHATTACHARYA S, MISHRA S. Applications of machine learning for facies and fracture prediction using Bayesian network theory and random forest:Case studies from the Appalachian basin,USA[J]. Journal of Petroleum Science & Engineering, 2018, 170:1005-1017.
[9]	钟庆良, 唐海, 石秀平, 等. 潜江凹陷潜江组盐间页岩油岩石物理建模研究[J]. 石油物探, 2020, 59(4):505-516. doi: 10.3969/j.issn.1000-1441.2020.04.002
	ZHONG Qingliang, TANG Hai, SHI Xiuping, et al. Rock physics modeling of inter-salt shale oil in the Qianjiang formation of Qianjiang sag,China[J]. Geophysical Prospecting for Petroleum, 2020, 59(4):505-516. doi: 10.3969/j.issn.1000-1441.2020.04.002
[10]	孙予舒, 黄芸, 梁婷, 等. 基于XGBoost算法的复杂碳酸盐岩岩性测井识别[J]. 岩性油气藏, 2020, 32(4):98-106.
	SUN Yushu, HUANG Yun, LIANG Ting, et al. Identification of complex carbonate lithology by logging based on XGBoost algorithm[J]. Lithologic Reservoirs, 2020, 32(4):98-106.
[11]	王胜, 赖昆, 张拯, 等. 基于随钻振动信号与深度学习的岩性智能预测方法[J]. 煤田地质与勘探, 2023, 51(9):51-63.
	WANG Sheng, LAI Kun, ZHANG Zheng, et al. Intelligent lithology prediction method based on vibration signal while drilling and deep learning[J]. Coal Geology & Exploration, 2023, 51(9):51-63.
[12]	安鹏, 曹丹平. 基于深度学习的测井岩性识别方法研究与应用[J]. 地球物理学进展, 2018, 33(3):1029-1034.
	AN Peng, CAO Danping. Research and application of logging lithology identification based on deep learning[J]. Progress in Geo physics, 2018, 33(3):1029-1034.
[13]	武中原, 张欣, 张春雷, 等. 基于LSTM循环神经网络的岩性识别方法[J]. 岩性油气藏, 2021, 33(3):120-128.
	WU Zhongyuan, ZHANG Xin, ZHANG Chunlei, et al. Lithology identification based on LSTM recurrent neural network[J]. Lithologic Reservoirs, 2021, 33(3):120-128.
[14]	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. doi: 10.6038/cjg20150528
	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.
[15]	李洪奇, 谭锋奇, 许长福, 等. 基于决策树方法的砾岩油藏岩性识别[J]. 测井技术, 2010, 34(1):16-21.
	LI Hongqi, TAN Fengqi, XU Changfu, et al. Lithology identification of conglomerate reservoir based on decision tree method[J]. Well Logging Technology, 2010, 34(1):16-21.
[16]	谷宇峰, 张道勇, 鲍志东. PSO-GBDT识别致密砂岩储集层岩性研究:以姬塬油田西部长4+5段为例[J]. 矿物岩石地球化学通报, 2021, 40(3):624-634.
	GU Yufeng, ZHANG Daoyong, BAO Zhidong, et al. Lithology prediction of tight sandstone reservoirs using the PSO-GBDT:A case study of the Chang 4+5 members in the western Jiyuan oilfield[J]. Bulletin of Mineralogy,Petrology and Geochemistry, 2021, 40(3):624-634.
[17]	潘拓, 马鑫, 谢安, 等. 利用主成分分析法优化BP神经网络模型在砂砾岩岩性识别中的应用[J]. 新疆地质, 2020, 38(3):417-420.
	PAN Tuo, MA Xin, XIE An, et al. Application of the optimized BP neural network model based on principal component analysis in lithology identification of glutenite reservoirs[J]. Xinjiang Geology, 2020, 38(3):417-420.
[18]	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.
[19]	崔俊峰, 杨金路, 王民, 等. 基于随机森林算法的泥页岩孔隙度预测[J]. 油气地质与采收率, 2023, 30(6):13-21.
	CUI Junfeng, YANG Jinlu, WANG Min, et al. Shale porosity prediction based on random forest algorithm[J]. Petroleum Geology and Recovery Efficiency, 2023, 30(6):13-21.
[20]	柴明锐, 程丹, 张昌民, 等. 机器学习方法对砂砾岩岩屑成分的预测:以西北缘X723井百口泉组为例[J]. 西安石油大学学报(自然科学版), 2017, 32(5):22-28.
	CHAI Mingrui, CHENG Dan, ZHANG Changmin, et al. Prediction of debris composition in glutenite by machine learning method:A case study in Baikouquan formation of Well X723 in the NW margin of Junggar basin[J]. Journal of Xi’an Shiyou University (Natural Science Edition), 2017, 32(5):22-28.
[21]	吴辰文, 梁靖涵, 王伟, 等. 基于递归特征消除方法的随机森林算法[J]. 统计与决策, 2017(21):60-63.
	WU Chenwen, LIANG Jinghan, WANG Wei, et al. Random forest algorithm based on recursive feature elimination[J]. Statistics & Decision, 2017(21):60-63.
[22]	周雪晴, 张占松, 张超谟, 等. 基于粗糙集—随机森林算法的复杂岩性识别[J]. 大庆石油地质与开发, 2017, 36(6):127-133.
	ZHOU Xueqing, ZHANG Zhansong, ZHANG Chaomo, et al. Complex lithologic identification based on rough set-random forest algorism[J]. Petroleum Geology & Oilfield Development in Daqing, 2017, 36(6):127-133.
[23]	刘超威, 李辉, 王泽胜, 等. 准噶尔盆地阜康凹陷二叠系上乌尔禾组油气勘探突破与启示[J]. 新疆石油地质, 2024, 45(2):139-150.
	LIU Chaowei, LI Hui, WANG Zesheng, et al. Breakthrough and implication of oil and gas exploration in Permian upper Wuerhe formation in Fukang sag,Junggar basin[J]. Xinjiang Petroleum Geology, 2024, 45(2):139-150.
[24]	张健, 刘楼军, 黄芸, 等. 准噶尔盆地吉木萨尔凹陷中—上二叠统沉积相特征[J]. 新疆地质, 2003, 21(4):412-414.
	ZHANG Jian, LIU Loujun, HUANG Yun, et al. Sedimentary characteristics of Middle-Upper Permian in Jimusaer sag of Junggar basin[J]. Xinjiang Geology, 2003, 21(4):412-414.
[25]	石军, 邹艳荣, 余江, 等. 准噶尔盆地阜康凹陷芦草沟组高有机碳页岩发育的古环境[J]. 天然气地球科学, 2018, 29(8):1138-1150. doi: 10.11764/j.issn.1672-1926.2018.06.016
	SHI Jun, ZOU Yanrong, YU Jiang, et al. Paleoenvironment of organic-rich shale from the Lucaogou formation in the Fukang sag,Junggar basin,China[J]. Natural Gas Geoscience, 2018, 29(8):1138-1150.
[26]	王正和, 丁邦春, 闫剑飞, 等. 准南芦草沟组沉积特征及油气勘探前景[J]. 西安石油大学学报(自然科学版), 2016, 31(2):25-32.
	WANG Zhenghe, DING Bangchun, YAN Jianfei, et al. Depositional characteristics and petroleum exploration significance of Lucaogou formation in south Junggar basin[J]. Journal of Xi’an Shiyou University(Natural Science Edition), 2016, 31(2):25-32.
[27]	匡立春, 孙中春, 欧阳敏, 等. 吉木萨尔凹陷芦草沟组复杂岩性致密油储层测井岩性识别[J]. 测井技术, 2013, 37(6):638-642.
	KUANG Lichun, SUN Zhongchun, OUYANG Min, et al. Complication lithology logging identification of the Lucaogou tight oil reservoir in Jimusaer depression[J]. Well Logging Technology, 2013, 37(6):638-642.
[28]	王伟, 赵延伟, 毛锐, 等. 页岩油储层核磁有效孔隙度起算时间的确定:以吉木萨尔凹陷二叠系芦草沟组页岩油储层为例[J]. 石油与天然气地质, 2019, 40(3):550-557.
	WANG Wei, ZHAO Yanwei, MAO Rui, et al. Determination of the starting time for measurement of NMR effective porosity in shale oil reservoir:A case study of the Permian Lucaogou shale oil reservoir,Jimusaer sag[J]. Oil & Gas Geology, 2019, 40(3):550-557.