3种经典机器学习算法在火山岩测井岩性识别中的对比

doi:10.13278/j.cnki.jjuese.20200210

摘要/Abstract

摘要： 岩性识别一直是火山岩油气勘探中的重要课题，基于测井数据的岩性识别也逐渐成为火山岩研究的需要，大数据背景下的机器学习算法为测井岩性识别提供了一个新方向。为提高某研究区火山岩岩性识别符合率，本文采用K近邻、支持向量机和自适应增强3种经典机器学习算法，对研究区内的粗面岩、非致密粗面岩、辉绿岩、辉长岩、玄武岩和非致密玄武岩等6类中基性火山岩进行岩性识别。从常规测井系列中优选对研究区岩性敏感的自然伽马、声波时差、补偿中子、深侧向电阻率和补偿密度等5种测井参数作为岩性识别模型的输入向量，从研究区内5口有岩心样品或薄片鉴定资料的目标层中选取测井数据点1 440个，其中960个作为训练样本，其余480个作为测试样本。以识别符合率和时间作为评价指标，对3种算法的识别结果进行对比分析，实验表明：自适应增强算法的分类准确率最高，6类岩性平均识别符合率达到82.10%；支持向量机算法表现良好，平均识别符合率为81.04%；K近邻算法平均识别符合率为76.04%。

关键词: K近邻, 支持向量机, 自适应增强算法, 火山岩, 岩性识别

Abstract: Lithology identification has always been an important project in oil and gas exploration of volcanic rocks, and based on logging data, it has become a need for volcanic rock research. Machine learning algorithms under the background of big data provide a new direction for logging lithology identification. In order to improve the lithology recognition accuracy of volcanic rocks in the study area, K-nearest neighbor (KNN), support vector machine (SVM), and adaptive boosting (Ada Boosting) various classic machine learning algorithms are used here to identify six types of volcanic rocks,which consist of basalt, non-compacted basalt, trachyte, non-compacted trachyte, gabbro and diabase. Five types of well logging parameters sensitive to the lithology of the study area are selected from the conventional logging series as input vectors. 1 440 logging data points are selected from five wells with core samples or segmented data, 960 of them are used as training samples, and the remaining 480 are used as test samples. Using recognition accuracy and time as evaluation indicators, the recognition results of the three algorithms are compared and analyzed. The experiments show that the classification accuracy of the Ada Boosting algorithm is the highest with an average recognition rate of 82.10% for six types of lithology; The SVM algorithm performs well with an average recognition rate of 81.04%; The recognition rate of KNN algorithm is 76.04%.

Key words: K nearest neighbor, support vector machine, Ada Boosting, volcanic rocks, lithology identification

中图分类号:

P631.8

牟丹, 张丽春, 徐长玲. 3种经典机器学习算法在火山岩测井岩性识别中的对比[J]. 吉林大学学报(地球科学版), 2021, 51(3): 951-956.

Mou Dan, Zhang Lichun, Xu Changling. Comparison of Three Classical Machine Learning Algorithms for Lithology Identification of Volcanic Rocks Using Well Logging Data[J]. Journal of Jilin University(Earth Science Edition), 2021, 51(3): 951-956.

参考文献

[1] 严伟,刘帅,冯明刚,等. 四川盆地丁山区块页岩气储层关键参数测井评价方法[J].岩性油气藏, 2019, 31(3): 95-104. Yan Wei, Liu Shuai, Feng Minggang, et al. Well Logging Evaluation Methods of Key Parameters for Shale Gas Reservoir in Ding-Shan Block, Sichuan Basin[J]. Lithologic Reservoirs, 2019, 31(3): 95-104.
[2] 王璞珺,缴洋洋,杨凯凯,等. 准噶尔盆地火山岩分类研究与应用[J].吉林大学学报(地球科学版), 2016, 46(4): 1056-1070. Wang Pujun, Jiao Yangyang, Yang Kaikai, et al. Classification of Volcanogenic Successions and Its Application to Volcanic Reservoir Exploration in the Junggar Basin, NW China[J]. Journal of Jilin University (Earth Science Edition), 2016, 46(4): 1056-1070.
[3] Wang W H, Wang P J, Wang Z W, et al. Identifying the Lithology of Volcanic Rocks by Using the Time-Frequency Features of Array Acoustic Logging Data[J]. Interpretation, 2020, 8(3): 1-38.
[4] 于洋,王祝文,宁琴琴,等.松辽盆地大庆长垣四方台组可地浸砂岩铀成矿测井评价[J].吉林大学学报(地球科学版), 2020,50(3):929-940. Yu Yang, Wang Zhuwen, Ning Qinqin, et al. Logging Evaluation of in Situ Leachable Sandstone Uranium Mineralization in Sifangtai Formation of Daqing Placantic Line, Songliao Basin[J].Journal of Jilin University (Earth Science Edition), 2020, 50(3): 929-940.
[5] 覃瑞东,林振洲,潘和平,等. 木里地区水合物及岩性测井识别方法[J].物探与化探, 2017, 41(6): 1088-1098. Qin Ruidong, Lin Zhenzhou, Pan Heping, et al. Identification of Hydrate and Lithology Based on Well Logs in Muli Area[J]. Geophysical and Geochemical Exploration, 2017, 41(6): 1088-1098.
[6] 冯冲,王清斌,谭忠健,等. 富火山碎屑地层复杂岩性测井分类与识别:以KL16油田为例[J].石油学报, 2019, 40(增刊2): 91-101. Feng Chong, Wang Qingbin, Tan Zhongjian, et al. Logging Classification and Identification of Complex Lithologies in Volcanic Debris-Rich Formations: An Example of KL16 Oilfield[J]. Acta Petrolei Sinica, 2019, 40(Sup.2): 91-101.
[7] 徐苗苗,印兴耀,宗兆云,等. 基于复合蛙跳算法的火山岩最优化测井解释方法[J].石油物探, 2020, 59(1): 122-130. Xu Miaomiao, Yin Xingyao, Zong Zhaoyun, et al. Logging Interpretation Optimization of Volcanic Rocks Using the Complex Frog-Leaping Algorithm[J]. Geophysical Prospecting for Petroleum, 2020, 59(1): 122-130.
[8] 孙予舒,黄芸,梁婷,等. 基于XG-Boost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, Hang Yun, Liang Ting, et al. Identification of Complex Carbonate Lithology by Logging Based on XG-Boost Algorithm[J]. Lithologic Reservoirs, 2020, 32(4): 98-106.
[9] 张野,李明超,韩帅. 基于岩石图像深度学习的岩性自动识别与分类方法[J].岩石学报, 2018, 34(2): 333-342. Zhang Ye, Li Mingchao, Han Shuai. Automatic Identification and Classification in Lithology Based on Deep Learning in Rock Images[J]. Acta Petrologica Sinica, 2018, 34(2): 333-342.
[10] 杨笑,王志章,周子勇,等. 基于参数优化Ada Boost算法的酸性火山岩岩性分类[J].石油学报, 2019, 40(4): 457-467. Yang Xiao, Wang Zhizhang, Zhou Ziyong, et al. Lithology Classification of Acidic Volcanic Rocks Based on Parameter-Optimized Ada Boost Algorithm[J]. Acta Petrolei Sinica, 2019, 40(4): 457-467.
[11] 苏赋,马磊,罗仁泽,等. 基于改进多分类孪生支持向量机的测井岩性识别方法研究与应用[J].地球物理学进展, 2020, 35(1): 174-180. Su Fu, Ma Lei, Luo Renze, et al. Research and Application of Logging Lithology Identification Based on Improve Multi-Class Twin Support Vector Machine[J]. Progress in Geophysics, 2020, 35(1): 174-180.
[12] 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. 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 Chinese[J]. Journal of Geophysics, 2015, 58(5): 1785-1793.
[13] Glowacz A, Glowacz Z. Recognition of Images of Finger Skin with Application of Histogram, Image Filtration and K-NN Classifier[J]. Biocybernetics and Biomedical Engineering, 2016, 36(1): 95-101.
[14] Rastegarzadeh G, Nemati M. Primary Mass Discrimination of High Energy Cosmic Rays Using PNN and K-NN Methods[J]. Advances in Space Research,2018, 61(4): 1181-1191.
[15] 曹莹,苗启广,刘家辰,等. Ada Boost算法研究进展与展望[J].自动化学报, 2013, 39(6): 745-758. Cao Ying, Miao Qiguang, Liu Jiachen, et al. Advance and Prospects of Ada Boost Algorithm[J]. Acta Automatica Sinica, 2013, 39(6): 745-758.

相关文章 15

[1]	唐华风, 张亚东, 邹明倬, 陆国超, 户景松, 张津铭, 卞海越. 渤海湾盆地莱州湾凹陷K油田中生界火山岩储层定量评价[J]. 吉林大学学报(地球科学版), 2026, 56(3): 739-753.
[2]	任宪军, 石云倩. 松辽盆地南部下白垩统火石岭组钙碱性火山岩地球化学特征及成因[J]. 吉林大学学报(地球科学版), 2026, 56(3): 818-834.
[3]	孙文博, 苟军, 王世成, 王常东, 王广婷, 孙家兴, 张铎, 田丽, 孙德有. 大兴安岭南部白音沙那盆地中生代火山岩年代学及岩石成因[J]. 吉林大学学报(地球科学版), 2026, 56(3): 852-874.
[4]	李新琦, 霍飞宇, 赵志平, 崔普媛, 李祺. 渤中凹陷中生界火山岩规模性裂缝储层特征及成因#br#[J]. 吉林大学学报(地球科学版), 2026, 56(2): 483-496.
[5]	黄玉龙, 张皓, 郭强, 陈昌. 低阻玄武岩的矿物学特征及其油气地质意义——以辽河坳陷古近系为例 [J]. 吉林大学学报(地球科学版), 2026, 56(2): 511-521.
[6]	杨兰, 王运, 邹勇军, 胡宝群, 李满根, 张安, 朱满怀. 基于机器学习的富硒土壤预测模型的构建与比较——以江西省信丰县油山地区为例[J]. 吉林大学学报(地球科学版), 2025, 55(5): 1629-1643.
[7]	吴燕清, 杨志亮, 王常东, 郝晓飞, 姜山, 林天发, 于兵, 董小宇, 张强, 周舰, 王天奇, 王一鸣. 内蒙古乌兰哈达—楚鲁达板地区铀矿化特征及找矿方向 [J]. 吉林大学学报(地球科学版), 2025, 55(4): 1103-1119.
[8]	曹志民, 张丽, 郑兵, 韩建. 基于SMOTE平衡数据的极端随机树岩性识别[J]. 吉林大学学报(地球科学版), 2025, 55(4): 1372-1386.
[9]	朱建峰, 张美华, 冷庆磊, 刘玉虎, 栾颖. 松辽盆地查干花次凹火山岩构造裂缝及应力场[J]. 吉林大学学报(地球科学版), 2025, 55(3): 745-757.
[10]	任梦怡, 范洪军, 陆国超, 柏佳伟, 唐华风. 渤海莱州湾凹陷南斜坡中生界火山岩储层特征和控制因素[J]. 吉林大学学报(地球科学版), 2025, 55(1): 15-30.
[11]	牛成民, 于海波, 单玄龙, 王冰洁, 郭景震, 邹玉洁, 庞赫, 衣健. 渤海海域锦州25-A构造区中生界火山岩有利储层成因[J]. 吉林大学学报(地球科学版), 2024, 54(6): 1788-1880.
[12]	徐春强, 王晨杰, 王蔚. 渤中凹陷北部中生界火山岩储层发育特征及油气成藏条件[J]. 吉林大学学报(地球科学版), 2024, 54(6): 1801-1814.
[13]	刘翔宇, 单玄龙, 衣健, 苏思远, 李嘉慧, 庞赫, 邹玉洁. 渤海湾盆地渤中凹陷义县组火山喷发旋回及其分布规律[J]. 吉林大学学报(地球科学版), 2024, 54(6): 1829-1845.
[14]	王庶丞, 唐华风, 邹明倬, 陆国超, 户景松. 渤海湾盆地莱州湾凹陷南部斜坡带中生界火山岩裂缝特征及分布规律[J]. 吉林大学学报(地球科学版), 2024, 54(6): 1846-1859.
[15]	郝国丽, 蒋迪娅, 许风光, 张昊, 金艳, 刘洋. 珠江口盆地恩平凹陷西南部火山岩相和火山机构特征及其分布控制因素[J]. 吉林大学学报(地球科学版), 2024, 54(6): 1951-1967.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed