基于XGBoost算法的砂砾岩储层测井岩性识别

doi:10.11885/j.issn.1674-5086.2024.06.12.01

西南石油大学学报(自然科学版) ›› 2025, Vol. 47 ›› Issue (5): 39-48.DOI: 10.11885/j.issn.1674-5086.2024.06.12.01

基于XGBoost算法的砂砾岩储层测井岩性识别

王英伟¹, 赵军², 覃建华³, 张景⁴, 汪峻宇², 冯月丽¹

1. 中国石油新疆油田公司勘探开发研究院, 新疆克拉玛依 834000;
2. 西南石油大学地球科学与技术学院, 四川成都 610500;
3. 怀柔实验室新疆研究院, 新疆乌鲁木齐 830000;
4. 中国石油新疆油田公司玛湖勘探开发项目部, 新疆克拉玛依 834000

收稿日期:2024-06-12 发布日期:2025-11-04
通讯作者: 王英伟，E-mail:xjwyw@petrochina.com.cn
作者简介:王英伟，1985年生，男，汉族，河南南阳人，高级工程师，主要从事非常规油藏开发地质研究工作。E-mail: xjwyw@petrochina.com.cn
赵军，1970年生，汉族，四川盐亭人，教授，博士，主要从事岩石物理理论及测井地质解释与评价研究工作。E-mail: zhaojun_70@126.com
覃建华，1970年生，男，汉族，四川宣汉人，教授级高级工程师，主要从事非常规油藏开发地质等方面的研究工作。E-mail: qjianhua@petrochina.com.cn
张景，1985年生，男，汉族，湖北罗田人，高级工程师，主要从事非常规油藏开发研究工作。E-mail:zhangjin_xj@petrochina.com.cn
汪峻宇，1999年生，男，汉族，四川广元人，硕士，主要从事测井地质解释与评价研究工作。E-mail:x18781208315@gmail.com
冯月丽，1984年生，女，汉族，山东菏泽人，高级工程师，主要从事非常规油藏压裂缝扩展数值模拟和油藏数值模拟工作。E-mail: fcgfyl2022@petrochina.com.cn

Lithology Identification in Glutenite Reservoir Based on the XGBoost Algorithm

WANG Yingwei¹, ZHAO Jun², QIN Jianhua³, ZHANG Jing⁴, WANG Junyu², FENG Yueli¹

1. Exploration and Development Research Institute, Xinjiang Oilfield Company, PetroChina, Karamay, Xinjiang 834000, China;
2. School of Geoscience and Technology, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
3. Xinjiang Research Institute of Huairou Laboratory, Urumqi, Xinjiang 830000, China;
4. Mahu Exploration and Development Project Department, Xinjiang Oilfield Company, PetroChina, Karamay, Xinjiang 834000, China

Received:2024-06-12 Published:2025-11-04

摘要/Abstract

摘要： 在砂砾岩储层的岩性识别中，岩石粒度的影响使测井曲线响应复杂，呈现低维线性不可分、高维可分的特点，传统的低维建模方法难以有效应对高维数据建模需求。随着人工智能技术的发展，基于测井数据和计算机算法的岩性识别方法逐渐成为研究趋势。应用优化版的梯度提升决策树算法XGBoost以提升M区块砂砾岩储层的岩性识别精度。虽然XGBoost已在岩性识别中广泛应用，但不同区块的岩性差异使其参数需进行区域适配优化。以百口泉组储层为研究对象，分析其岩性特征及测井响应特征，并选择GR、AC、DEN和R_T测井曲线作为特征变量。对468组样本按4： 1的比例划分训练集和测试集，并通过交叉验证优化XGBoost的关键参数，确定了最佳的迭代次数和学习率等参数。实验结果显示，XGBoost算法在本区块的岩性识别准确率达91.05%，相较于C4.5决策树算法，在识别精度和效率上均有显著提升。研究结果验证了XGBoost在砂砾岩储层岩性识别中的适用性和有效性，为类似储层的勘探开发提供了技术参考。

关键词: XGBoost算法, 砂砾岩储层, 岩性识别, 测井评价, 百口泉组储层, 玛湖凹陷

Abstract: In glutenite reservoirs, the complexity of logging responses due to rock granularity poses challenges for traditional lithology identification methods. With technological advancements, combining logging data with computer technology for lithology research has become a new trend. The optimized version of the gradient boosting decision tree, the XGBoost algorithm, is widely applied in lithology identification for its efficient and accurate prediction capabilities and excellent generalization performance. This study uses the XGBoost algorithm to identify the lithology of glutenite reservoirs in the M block to improve identification accuracy. By analyzing the lithological characteristics and logging responses of the Baikouquan formation reservoirs, four logging curves (GR, AC, DEN, R_T) were selected as feature variables. A total of 468 sample data sets were divided into training and testing sets in 4： 1 ratio, and the key parameters of XGBoost were optimized through cross-validation, determining the optimal values for iteration times, learning rate, and other model parameters. The experimental results show that the XGBoost algorithm performs well in lithology identification, achieving a final accuracy rate of 91.05%, an improvement in both accuracy and efficiency compared to the C4.5 decision tree algorithm. The study results demonstrate the effectiveness of the XGBoost algorithm in improving lithology identification accuracy, providing guidance for the exploration and development of glutenite reservoirs.

Key words: XGBoost algorithm, glutenite reservoir, lithology identification, logging evaluation, Baikouquan Formation Reservoir, Mahu Depression

中图分类号:

TE121

王英伟, 赵军, 覃建华, 张景, 汪峻宇, 冯月丽. 基于XGBoost算法的砂砾岩储层测井岩性识别[J]. 西南石油大学学报(自然科学版), 2025, 47(5): 39-48.

WANG Yingwei, ZHAO Jun, QIN Jianhua, ZHANG Jing, WANG Junyu, FENG Yueli. Lithology Identification in Glutenite Reservoir Based on the XGBoost Algorithm[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2025, 47(5): 39-48.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal15.magtechjournal.com/Jwk_xnzk/CN/10.11885/j.issn.1674-5086.2024.06.12.01

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2025/V47/I5/39

参考文献

[1] LIU Jingjing, LIU Jianchao. An intelligent approach for reservoir quality evaluation in tight sandstone reservoir using gradient boosting decision tree algorithm A case study of the Yanchang Formation, mid-eastern Ordos Basin, China (Article)[J]. Marine and Petroleum Geology, 2021, 126:104939. doi:10.1016/j.marpetgeo.2021.104939
[2] GUO Yufeng, BAO Zhidong, SONG Xinmin, et al. Complex lithology prediction using probabilistic neural network improved by continuous restricted Boltzmann machine and particle swarm optimization[J]. Journal of Petroleum Science & Engineering, 2019, 179:966-978. doi:10.1016/j.petrol.2019.05.032
[3] XIE Yunxin, ZHU Chenyang, HU Runshan, et al. A coarse-to-fine approach for intelligent logging lithology identification with extremely randomized trees[J]. Mathematical Geosciences, 2021, 53(5):1-18. doi:10.1007/s11004-020-09885-y
[4] 颜世翠. 基于机器学习算法和属性特征双优选的砂体岩性预测方法[J]. 油气地质与采收率, 2022, 29(1):98-106. doi:10.13673/j.cnki.cn37-1359/te.2022.01.012 YAN Shicui. Prediction method of sandstone lithology based on optimized machine learning algorithms and attribute features[J]. Petroleum Geology and Recovery Efficiency, 2022, 29(1):98-106. doi:10.13673/j.cnki.cn37-1359/te.2022.01.012
[5] 王雷,韩学彪,曹英权,等. 基于对应分析的丽水椒江凹陷潜山岩性识别方法[J]. 石油钻探技术, 2024, 52(1):140-145. doi:10.11911/syztjs.2024019 WANG Lei, HAN Xuebiao, CAO Yingquan, et al. A lithology identification method for buried hills in the Lishui-Jiaojiang Sag based on correspondence analysis[J]. Petroleum Drilling Techniques, 2024, 52(1):140-145. doi:10.11911/syztjs.2024019
[6] 管耀,王清辉,冯进,等. 基于机器学习的蚀变火成岩测录井综合岩性识别[J]. 吉林大学学报(地球科学版), 2024, 54(1):345-358. doi:10.13278/j.cnki.jjuese.20220310 GUAN Yao, WANG Qinghui, FENG Jin, et al. Comprehensive lithology recognition of altered igneous reservoirs based on machine learning for wireline and cutting logs in Huizhou Depression, Pearl River Mouth Basin, northern south China Sea[J]. Journal of Jilin University(Earth Science Edition), 2024, 54(1):345-358. doi:10.13278/j.cnki.jjuese.20220310
[7] 张凤博,马雪玲,董珍珍,等. 基于CNN和LSTM的机器学习模型在测井岩性识别的应用[J]. 西安石油大学学报(自然科学版), 2024, 39(5):96-103, 133. doi:10.3969/j.issn.1673-064X.2024.05.012 ZHANG Fengbo, MA Xueling, DONG Zhenzhen, et al. Application of machine learning model based on CNN and LSTM in well logging lithology identification[J]. Journal of Xi'an Shiyou University (Natural Science Edition), 2024, 39(5):96-103, 133. doi:10.3969/j.issn.1673-064X.2024.05.012
[8] 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. doi:10.12108/yxyqc.20200410 SUN Yushu, HUANG Yun, LIANG Ting, et al. Lithology identification of complex carbonate reservoirs using XGBoost algorithm[J]. Lithologic Oil & Gas Reservoirs, 2020, 32(4):98-106. doi:10.12108/yxyqc.20200410
[9] 张翔,肖小玲,严良俊,等. 基于模糊支持向量机方法的岩性识别[J]. 石油天然气学报, 2009, 31(6):115-118, 184. doi:10.3969/j.issn.1000-9752.2009.06.021 ZHANG Xiang, XIAO Xiaoling, YAN Liangjun, et al. Lithology identification based on fuzzy support vector machine method[J]. Petroleum Science and Technology, 2009, 31(6):115-118, 184. doi:10.3969/j.issn.1000- 9752.2009.06.021
[10] 赵忠军,黄强东,石林辉,等. 基于BP神经网络算法识别苏里格气田致密砂岩储层岩性[J]. 测井技术, 2015, 39(3):363-367. doi:10.16489/j.issn.1004- 1338.2015.03.020 ZHAO Zhongjun, HUANG Qiangdong, SHI Linhui, et al. Lithology identification of tight sandstone reservoirs in Surige Gas Field based on BP neural network algorithm[J]. Well Logging Technology, 2015, 39(3):363-367. doi:10.16489/j.issn.1004-1338.2015.03.020
[11] 宋延杰,王团,付健,等. 雷64区块砂砾岩储层岩性识别方法研究[J]. 哈尔滨商业大学学报(自然科学版), 2015, 31(1):73-78, 89. doi:10.3969/j.issn.1672- 0946.2015.01.019 SONG Yanjie, WANG Tuan, FU Jian, et al. Study on lithology identification method of conglomerate reservoirs in Lei 64 Block[J]. Journal of Harbin University of Commerce (Natural Science Edition), 2015, 31(1):73-78, 89. doi:10.3969/j.issn.1672-0946.2015.01.019
[12] 韩启迪,张小桐,申维. 基于梯度提升决策树(GBDT)算法的岩性识别技术[J]. 矿物岩石地球化学通报, 2018, 37(6):1173-1180. doi:10.19658/j.issn.1007-2802.2019.38.009 HAN Qidi, ZHANG Xiaotong, SHEN Wei. Lithology identification technique based on gradient boosting decision tree (GBDT) algorithm[J]. Bulletin of Mineral, Rock and Geochemistry, 2018, 37(6):1173-1180. doi:10.19658/j.issn.1007-2802.2019.38.009
[13] 王恒,姜亚楠,张欣,等. 基于梯度提升算法的岩性识别方法[J]. 吉林大学学报(地球科学版), 2021, 51(3):940-950. doi:10.13278/j.cnki.jjuese.20200081 WANG Heng, JIANG Ya'nan, ZHANG Xin, et al. Lithology identification method based on gradient boosting algorithm[J]. Journal of Jilin University (Earth Science Edition), 2021, 51(3):940-950. doi:10.13278/j.cnki.jjuese.20200081
[14] JEROME H F. Greedy function approximation:A gradient boosting machine[J]. The Annals of Statistics, 2001, 29(5):1189-1232.
[15] 闫星宇,顾汉明,肖逸飞,等. XGBoost算法在致密砂岩气储层测井解释中的应用[J]. 石油地球物理勘探, 2019, 54(2):447-455, 241. doi:10.13810/j.cnki.issn.1000-7210.2019.02.024 YAN Xingyu, GU Hanming, XIAO Yifei, et al. Application of XGBoost algorithm in well logging interpretation of tight sandstone gas reservoirs[J]. Oil Geophysical Prospecting, 2019, 54(2):447-455, 241. doi:10.13810/j.cnki.issn.1000-7210.2019.02.024
[16] 丁阳阳,赵军龙,李兆明,等. 基于XGBoost算法的煤体结构测井识别技术研究[J]. 地球物理学进展, 2022, 37(3):998-1006. doi:10.6038/pg2022FF0435 DING Yangyang, ZHAO Junlong, LI Zhaoming, et al. Well logging identification of coal structure based on XGBoost algorithm[J]. Progress in Geophysics, 2022, 37(3):998-1006. doi:10.6038/pg2022FF0435
[17] 宋涛,黄福喜,汪少勇,等. 准噶尔盆地玛湖凹陷侏罗系油气藏特征及勘探潜力[J]. 中国石油勘探, 2019, 24(3):341-350. doi:10.3969/j.issn.1672-7703.2019.03.007 SONG Tao, HUANG Fuxi, WANG Shaoyong, et al. Characteristics and exploration potential of Jurassic oil and gas reservoirs in the Mahu Depression, Junggar Basin[J]. China Petroleum Exploration, 2019, 24(3):341-350. doi:10.3969/j.issn.1672-7703.2019.03.007
[18] 陈程,彭梦芸,赵婷,等. 玛湖凹陷北、西斜坡区百口泉组储集层对比及勘探启示[J]. 新疆石油地质, 2022, 43(1):18-25. doi:10.7657/XJPG20220103 CHEN Cheng, PENG Mengyun, ZHAO Ting, et al. Reservoir correlation and exploration implications of the Baikouquan Formation in the northern and western slope areas of the Mahu Sag[J]. Xinjiang Petroleum Geology, 2022, 43(1):18-25. doi:10.7657/XJPG20220103
[19] 靳军,康逊,胡文瑄,等. 准噶尔盆地玛湖凹陷西斜坡百口泉组砂砾岩储层成岩作用及对储集性能的影响[J]. 石油与天然气地质, 2017, 38(2):323-333, 406. doi:10.11743/ogg20170212 JIN Jun, KANG Xun, HU Wenxuan, et al. Diagenesis of Baikouquan Formation conglomerate reservoirs in the western slope of the Mahu Sag, Junggar Basin, and its influence on reservoir properties[J]. Oil & Gas Geology, 2017, 38(2):323-333, 406. doi:10.11743/ogg20170212
[20] 付瑜,柳益群,蒋宜勤,等. 准噶尔盆地西北缘玛湖凹陷三叠系百口泉组砂砾岩储层孔隙结构及渗流特征[J]. 西北地质, 2020, 53(2):223-234. doi:10.19751/j.cnki.61-1149/p.2020.02.014 FU Yu, LIU Yiqun, JIANG Yiqin, et al. Pore structure and flow characteristics of Triassic Baikouquan Formation conglomerate reservoirs in the northwestern margin of the Mahu Sag, Junggar Basin[J]. Northwest Geology, 2020, 53(2):223-234. doi:10.19751/j.cnki.61-1149/p.2020.02.014
[21] 罗水亮,漆影强,唐松,等. 基于改进Stacking算法的碳酸盐岩储层测井岩性识别方法与应用[J]. 特种油气藏, 2025, 32(4):58-67. doi:10.3969/j.issn.1006- 6535.2025.04.007 LUO Shuiliang, QI Yingqiang, TANG Song, et al. Lithology identification method and application of carbonate reservoirs from well logging based on an improved Stacking algorithm[J]. Special Oil & Gas Reservoirs, 2025, 32(4):58-67. doi:10.3969/j.issn.1006-6535.2025.04.007

基于XGBoost算法的砂砾岩储层测井岩性识别

Lithology Identification in Glutenite Reservoir Based on the XGBoost Algorithm

RichHTML

PDF (PC)

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]	王伟俊, 刘红岐, 朱光亚, 辛炯垄, 王友净. 碳酸盐岩油藏储层测井挖掘效应的综合分析[J]. 西南石油大学学报(自然科学版), 2023, 45(1): 43-54.
[2]	刘成川, 陈俊, 程洪亮. 川西致密砂岩气藏测井评价技术及其发展展望[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 59-69.
[3]	谭龙, 王晓光, 程宏杰, 张记刚, 廉桂辉. 玛湖致密砾岩油藏注烃类气混相驱油藏数值模拟[J]. 西南石油大学学报(自然科学版), 2021, 43(5): 193-202.
[4]	田瀚, 张建勇, 李昌, 李文正, 姚倩颖. 成像测井在灯影组微生物岩岩相识别中的应用[J]. 西南石油大学学报(自然科学版), 2020, 42(5): 75-85.
[5]	钱海涛, 尤新才, 魏云, 白雨, 吴俊. 玛东地区百口泉组地层新认识及油气勘探意义[J]. 西南石油大学学报(自然科学版), 2020, 42(2): 27-36.
[6]	魏兵, 宋涛, 赵金洲, 卡杰特·瓦列里, 蒲万芬. 溶解气回注提高致密油藏采收率效果及敏感性[J]. 西南石油大学学报(自然科学版), 2019, 41(5): 85-95.
[7]	印森林, 陈恭洋, 陈玉琨, 吴小军. 砂砾岩储层孔隙结构复杂模态差异机制[J]. 西南石油大学学报(自然科学版), 2019, 41(1): 1-17.
[8]	刘海磊, 尹鹤, 陈刚强, 李啸, 杨帆. 玛湖凹陷及周缘石炭系储层与流体相态预测[J]. 西南石油大学学报(自然科学版), 2017, 39(5): 41-50.
[9]	任本兵, 瞿建华, 王泽胜, 钱海涛, 唐勇. 玛湖凹陷三叠纪古地貌对沉积的分级控制作用[J]. 西南石油大学学报(自然科学版), 2016, 38(5): 81-89.
[10]	王彬1 *，邱恩波2，庞晶1，席燕卿3，崔国强1. 新疆H 储气库改建关键问题测井评价[J]. 西南石油大学学报(自然科学版), 2016, 38(1): 46-52.
[11]	张宪国1 *，张涛2，林承焰1，于景锋3. 塔南凹陷复杂岩性低渗透储层测井岩性识别[J]. 西南石油大学学报(自然科学版), 2015, 37(1): 85-90.
[12]	王坤1，张奉2，张翊2，王东坤3. 准西车排子凸起石炭系岩性识别与储层特征[J]. 西南石油大学学报(自然科学版), 2014, 36(4): 21-28.
[13]	陈刚强1，阿布力米提1，白雷2，张家浩1，卞保力1. 准噶尔盆地玛湖凹陷东斜坡深层成藏领域研究[J]. 西南石油大学学报(自然科学版), 2013, 35(6): 31-38.
[14]	洪忠;苏明军;刘化清;张晶;蔡刚. 复杂岩性地区岩性识别与储层预测[J]. 西南石油大学学报(自然科学版), 2012, 34(6): 38-46.
[15]	陈克勇a;b 段新国b 张小兵b 宋荣彩b . 基于三维岩相建模的火山岩岩性识别与预测[J]. 西南石油大学学报(自然科学版), 2010, 32(2): 19-24.