Identification of lithologic characteristics of volcanic rocks by support vector machine

doi:10.7623/syxb201302013

Editorial office of ACTA PETROLEI SINICA ›› 2013, Vol. 34 ›› Issue (2): 312-322.DOI: 10.7623/syxb201302013

• Petroleum Exploration • Previous Articles Next Articles

Identification of lithologic characteristics of volcanic rocks by support vector machine

ZHU Yixiang SHI Guangren

Received:2012-07-04 Revised:2012-10-28 Online:2013-03-25 Published:2013-01-31

火山岩岩性的支持向量机识别

朱怡翔石广仁

通讯作者: 朱怡翔
作者简介:朱怡翔，男，1960年2月生，1982年获合肥工业大学学士学位，2004年获中国地质大学(北京)博士学位，现为中国石油勘探开发研究院教授级高级工程师、博士生导师，主要从事储层地质、地震和测井的综合表征和预测、复杂岩性储层的测井评价等研究工作。
基金资助:
国家重大基础研究发展计划(973)项目“高效天然气藏形成分布与凝析、低效气藏经济开发的基础研究”(2008CB209100)资助。

Abstract

Abstract:

A model to characterize lithology of volcanic rock reservoirs by using nine types of volcanic rocks was presented to indicate lithologic control over high-quality reservoirs. Based on this model, we selected 15 petrogeophysical logging parameters sensitive to lithology, fabrics, genesis and pore structures of volcanic rocks, and adopted three machine learning algorithms, i.e. multiple regression analysis (MRA), artificial neural network (ANN) and support vector machine (SVM), respectively, to identify lithologic characteristics of volcanic rocks. Taking the Niudong oilfield of the Malang sag in the Santanghu Basin as an example, we employed data from three wells where volcanic rock reservoirs in Well N9-10 and Well N9-19 served as learning samples while that in Well N8-10 as a prediction sample. In particular, 1361 samples from Well N9-10 and 881 samples from Well N9-19 were employed and each of them contained 15 parameters of logging and lithology, the knowledge to predict lithologic characteristics of volcanic rocks could be obtained, respectively, by these algorithms. Then, 961 samples from Well N8-10 were used and each sample only had 15 logging parameters, while their lithologic characteristics were gained based on the aforementioned knowledge obtained by learning. The result shows that as for the learning samples, the absolute value of mean relative errors (%) between calculated and field-measured results for MRA, ANN and SVM are 51.84%, 48.66% and 0, respectively; and as for the prediction samples, these errors are 52.44%, 46.31% and 6.30%, respectively. Therefore, in this case only SVM is applicable because a nonlinear relationship between lithologic characteristics of volcanic rocks and 15 petrogeophysical logging parameters is very strong.

Key words: volcanic rock, lithologic division, reservoir, petrogeophysical logging, multiple regression analysis (MRA), artificial neural network (ANN), support vector machine (SVM)

摘要：

提出了用9种火山岩的岩石类型描述火山岩储层岩性的模型，表达岩性对优质储层的控制作用。基于该模型，选取了对火山岩的岩性、组构、成因和孔隙结构反应灵敏的15种岩石物理测井参数，分别采用多元回归分析（MRA）、人工神经网络（ANN）和支持向量机（SVM）3种机器学习算法，尝试火山岩岩性的识别。在三塘湖盆地马朗凹陷牛东油田的实例中，使用了3口井的数据，其中N9-10井和N9-19井的火山岩储层为学习样本，N8-10井的火山岩储层为预测样本。利用N9-10井1361个样本和N9-19井881个样本（每个样本含15种测井参数及岩性），通过这3种机器学习算法分别获得预测火山岩岩性的知识;然后，利用N8-10井961个样本（每个样本仅含15种测井参数），根据上述学习获得的知识，得到这961个样本的岩性。研究发现：对于学习样本，MRA、ANN和SVM的计算与实际的平均相对误差绝对值分别为51.84%，48.66%和0;对于预测样本，则分别为52.44%，46.31%和6.30%。实例分析表明，只有SVM适用于本实例，这是由于火山岩岩性与15种岩石物理测井参数的非线性关系十分强烈。

关键词: 火山岩, 岩性划分, 储层, 岩石物理测井, 多元回归分析, 人工神经网络, 支持向量机

ZHU Yixiang SHI Guangren. Identification of lithologic characteristics of volcanic rocks by support vector machine[J]. Editorial office of ACTA PETROLEI SINICA, 2013, 34(2): 312-322.

朱怡翔石广仁. 火山岩岩性的支持向量机识别[J]. 石油学报, 2013, 34(2): 312-322.

References

[1] 范宜仁，黄隆基，代诗华.交会图技术在火山岩岩性与裂缝识别中的应用[J].测井技术，1999，23（1）：53-56，64.

Fan Yiren，Huang Longji，Dai Shihua.Application of crossplot technique to the determination of lithology composition and fracture identification of igneous rock[J].Well Logging Technology，1999，23（1）：53-56，64.

[2] 王拥军，周雪峰，吴海忠，等.火山岩岩性识别新技术[J].断块油气田，2006，13（3）：86-88.

Wang Yongjun，Zhou Xuefeng，Wu Haizhong，et al.A new technique of lithologic identification for volcanics[J].Fault-block Oil & Gas Field，2006，13（3）：86-88.

[3] 赵新建，胡刚，张梦宁，等.火山岩岩性识别方法研究[J].国外测井技术，2011，31（6）：28-30，33.

Zhao Xinjian，Hu Gang，Zhang Mengning，et al.A study on lithology identification methods for volcanic rocks[J].World Well Logging Technology，2011，31（6）：28-30，33.

[4] 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（增刊）：62-65.

Liu Chuanping，Zheng Jiandong，Yang Jingqiang.Lithology identification of well logging for deep volcanic reservoir in Xushen Gas Field[J].Acta Petrolei Sinica，2006，27（S1）：62-65.

[5] 于代国，孙建孟，王焕增，等.测井识别岩性新方法--支持向量机方法[J].大庆石油地质与开发，2005，24（5）：93-95.

Yu Daiguo，Sun Jianmeng，Wang Huanzeng，et al.A new method for logging lithology identification:SVM[J].Petroleum Geology & Oilfield Development in Daqing，2005，24（5）：93-95.

[6] 李新虎.基于不同测井曲线参数集的支持向量机岩性识别对比[J].煤田地质与勘探，2007，35（7）：72-76，80.

Li Xinhu.Lithology identification methods contrast based on support vector machines at different well logging parameter[J].Coal Geology & Exploration，2007，35（7）：72-76，80.

[7] 马海，王延江，胡睿，等.测井岩性识别新方法研究[J].地球物理学进展，2009，24（1）：263-269.

Ma Hai，Wang Yanjiang，Hu Rui，et al.A novel method for well logging lithologic identification[J].Progress in Geophysics，2009，24（1）：263-269.

[8] 文政，高松洋，毕广武.支持向量机在复杂岩性测井识别中的应用[J].大庆石油地质与开发，2009，28（2）：134-137.

Wen Zheng，Gao Songyang，Bi Guangwu.Application of support vector machine （SVM）in complex lithology identification by well logging[J].Petroleum Geology & Oilfield Development in Daqing，2009，28（2）：134-137.

[9] 钟仪华，李榕.基于主成分分析的最小二乘支持向量机岩性识别方法[J].测井技术，2009，33（5）：425-429.

Zhong Yihua，Li Rong.Application of principal component analysis and least square support vector machine to lithology identification[J].Well Logging Technology，2009，33（5）：425-429.

[10] 程国建，郭瑞华.PSO-LSSVM分类模型在岩性识别中的应用[J].西安石油大学学报：自然科学版，2010，25（1）：96-99.

Cheng Guojian，Guo Ruihua.Application of PSO-LSSVM classification model in logging lithology recognition[J].Journal of Xi'an Shiyou University:Natural Science Edition，2010，25（1）：96-99.

[11] 张莹，潘保芝.支持向量机与微电阻率成像测井识别火山岩岩性[J].物探与化探，2011，35（5）：634-638，642.

Zhang Ying，Pan Baozhi.The application of SVM and FMI to the lithologic identification of volcanic rocks[J].Geophysical and Geochemical Exploration，2011，35（5）：634-638，642.

[12] LeMaitre R W.A proposal by the IUGS subcommission on the systematics of igneous rocks for a chemical classification of volcanic rocks based on total alkali silica (TAS)diagram[J].Australian Journal of Earth Science，1984，31（2）：243-255.

[13] 邱家骧.国际地科联火成岩分类学分委会推荐的火山岩分类简介[J].现代地质，1991，5（4）：457-468.

Qiu Jiaxiang.Brief introduction of a classification of volcanic rocks recommendations of the IUGS subcommission on the systematics of igneous rocks[J].Geoscience，1991，5（4）：457-468.

[14] Song Xinmin,Zhu Yixiang,Liu Qinghuai,et al.Identification and distribution of natural fractures[R].SPE 50877,1998.

[15] 雍世和，洪有密.测井资料综合解释与数字处理[M].北京：石油工业出版社，1982：305-306.

Yong Shihe，Hong Youmi.Integrated interpretation and digital processing of well logging data[M].Beijing：Petroleum Industry Press，1982：305-306.

[16] 石广仁，张光亚，石骁騑.多地质因素的勘探目标优选--人工神经网络法与多元回归分析法比较研究[J].石油学报，2002，23（5）：19-22.

Shi Guangren，Zhang Guangya，Shi Xiaofeng.Optimization of exploration prospects based on multi-geological factors：comparison of methods between artificial neural network and multiple regression analysis[J].Acta Petrolei Sinica，2002，23（5）：19-22.

[17] Shi Guangren，Zhou Xingxi，Zhang Guangya，et al.The use of artificial neural network analysis and multiple regression for trap quality evaluation：a case study of the northern Kuqa depression of Tarim Basin in western China[J].Marine and Petroleum Geology，2004，21（3）：411-420.

[18] 石广仁.地学数据挖掘与知识发现[M].北京：石油工业出版社，2012：34-86.

Shi Guangren.Data mining and knowledge discovery for geosciences[M].Beijing：Petroleum Industry Press，2012：34-86.

[19] Shi Guangren.Four classifiers used in data mining and knowledge discovery for petroleum exploration and development[J].Advances in Petroleum Exploration and Development，2011,2（2）：12-23.

[20] Vapnik V N.统计学习理论的本质[M].张学工，译.北京：清华大学出版社，2000：85-205.

Vapnik V N.The nature of statistical learning theory[M].Translated by Zhang Xuegong.Beijing：Tsinghua University Press，2000：85-205.

[21] Cristianini N，Shawe-Taylor J.支持向量机导论[M]．李国正，王猛，曾华军，译.北京：电子工业出版社，2004：8-149.

Cristianini N，Shawe-Taylor J.An introduction to support vector machines[M].Translated by Li Guozheng，Wang Meng，Zeng Huajun.Beijing：Publishing House of Electronics Industry，2004：8-149.

[22] Schlkopf B，Smola A J，Williamson R C，et al.New support vector algorithms[J].Neural Computation，2000，12（5）：1207-1245.

[23] 石广仁.支持向量机在多地质因素分析中的应用[J].石油学报，2008，29（2）：195-198.

Shi Guangren.Application of support vector machine to multi-geological-factors analysis[J].Acta Petrolei Sinica，2008，29（2）：195-198.

[24] 李洪奇，郭海峰，郭海敏，等.复杂储层测井评价数据挖掘方法研究[J].石油学报，2009，30（4）：542-549.

Li Hongqi，Guo Haifeng，Guo Haimin，et al.An approach of data mining for evaluation of complex formation using well logs[J].Acta Petrolei Sinica，2009，30（4）：542-549.

[25] Shi G R.The use of support vector machine for oil and gas identification in low-porosity and low-permeability reservoirs[J].International Journal of Mathematical Modeling and Numerical Optimization，2009，1（1/2）：75-87.

[26] 石广仁.数据挖掘在石油勘探数据库中的应用前景[J].中国石油勘探，2009，14（1）：60-64.

Shi Guangren.Prospect of the application of data mining in petroleum exploration databases[J].China Petroleum Exploration，2009，14（1）：60-64.

Identification of lithologic characteristics of volcanic rocks by support vector machine

火山岩岩性的支持向量机识别

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Wang Xin, Meng Qi'an, Bai Yunfeng, Zhang Jinyou, Wang Min, Liu Zhao, Sun Xianda, Li Jinbu, Xu Chengwu, Xu Liang, Deng Zixiao, Wu Yan, Lu Shuangfang. Millimeter-scale fine evaluation and significance of shale reservoir performance and oil-bearing property:a case study of Member 1 of Q ingshankou Formation in Songliao Basin [J]. Acta Petrolei Sinica, 2024, 45(6): 961-975.
[2]	Xu Baochang, You Xiangning, Meng Zhuoran, Liu Wei, Yin Shixuan. Real-time formation pressure inversion method based on back-pressure excitation response [J]. Acta Petrolei Sinica, 2024, 45(6): 1009-1018.
[3]	Zhou Lihong, Chen Changwei, Yang Fei, Li Hongjun, Liu Guoquan, Cui Yu, Wu Xuesong, Shi Qianru, Xu Wenjing, Dong Wentao. Accumulation models and exploration practice of tight oil and gas in the deep sag areas of continental fault basins:a case study of Huanghua depression in Bohai Bay Basin [J]. Acta Petrolei Sinica, 2024, 45(5): 755-770.
[4]	Wang Qinghua. Breakthrough and significance of oil and gas exploration of Upper Cambrian Xiaqiulitage Formation in Kalayuergun structural belt,western Tabei uplift [J]. Acta Petrolei Sinica, 2024, 45(4): 615-628.
[5]	Lu Xuesong, Gui Lili, Wang Zecheng, Liu Shaobo, Liu Qiang, Fan Junjia, Chen Weiyan, Ma Xingzhi, Jiang Hua, Fu Xiaodong, Li Wenzheng, Zhong Yuan, Li Kunyu, Xie Wuren. Activity time of strike-slip faults and their controlling effects on hydrocarbon accumulation in central Sichuan Basin: evidence from U-Pb dating and fluid inclusions of cements in fault zone [J]. Acta Petrolei Sinica, 2024, 45(4): 642-658.
[6]	He Wenyuan, Huang Xianxiong, Wang Hongping, Wang Wangquan, Fan Guozhang, Ding Liangbo, Zhao Junfeng, Zhu Xiaohui, Zhang Yonggang, Pang Xu, Li Weiqiang, Zuo Guoping, Yang Liu, Wang Chaofeng. Hydrocarbon discovery and its significance of Well Gulashao-1 in deepwater area of Santos Basin, South America [J]. Acta Petrolei Sinica, 2024, 45(2): 339-347.
[7]	Zhang Chunyu, Chen Shijia, Zhu Xingcheng, Li Yong, Liu Guanglin, Li Yaoting, Zhang Yangyang, Gu Tianfu. Classification and characteristics of source-reservoir interlayer and its controlling effect on oil-gas enrichment in continental tight reservoir [J]. Acta Petrolei Sinica, 2024, 45(2): 358-373.
[8]	Yang Debin, He Xinming, Zhang Heng, Wang Yan, Liu Yao, Wang Ming. Intelligent identification of Ordovician epikarst zones and development laws of fractures and vugs in the main area of Tahe oilfield [J]. Acta Petrolei Sinica, 2024, 45(2): 374-389,411.
[9]	Liu Yongge, Li Guo, Jia Wei, Bai Yajie, Hou Jian, Clarke M A, Xu Hongzhi, Zhao Ermeng, Ji Yunkai, Chen Litao, Guo Tiankui, He Jiayuan, Zhang Le. Influence law of reservoir stimulation on depressurization exploitation of class Ⅰ natural gas hydrate reservoir [J]. Acta Petrolei Sinica, 2024, 45(2): 412-426,460.
[10]	Wu Baocheng, Wu Chengmei, Tan Qiang, Chu Yanjie, Liang Chenggang, Li Wenbo, Zhang Jinfeng, Chen Yiwei, Xu Tianlu, Wang Liangzhe. Accumulation conditions and key technologies for exploration and development of Changji shale oil in Jimusar sag of Junggar Basin [J]. Acta Petrolei Sinica, 2024, 45(2): 437-460.
[11]	Li Le, Hu Yuanqing, Peng Xiaogui, Wang Wei, Yu Haoyu, Cui Yasheng. Research progress of hydrogen sulfide genesis in shale gas reservoirs [J]. Acta Petrolei Sinica, 2024, 45(2): 461-476.
[12]	Zhi Dongming, Li Jianzhong, Zhou Zhichao, Jiao Lixin, Fan Tanguang, Li Bin, Liang Hui, Wang Xinggang. New fields, new types and resource potentials of oil-gas exploration and development in Santanghu Basin [J]. Acta Petrolei Sinica, 2024, 45(1): 115-132.
[13]	Zhang Hongan, Li Lingxi, Chen Qingtang, Wan Jing, Shi Dahai, Peng Guotao, Zhou Yongshui. New fields, new types and resource potentials of oil-gas exploration in Yin'gen-Ejinaqi Basin [J]. Acta Petrolei Sinica, 2024, 45(1): 147-162.
[14]	Tan Maojin, Wu Hongliang, Wang Siyu, Du Guanghui, Bai Yang, Wang Qian. Progress and development direction of log interpretation technology for marine shale gas in China [J]. Acta Petrolei Sinica, 2024, 45(1): 241-260.
[15]	Guo Qiulin, Huang Shaoying, Lu Yuhong, Wang Jian, Wu Xiaozhi, Chen Ningsheng. Modeling and resource distribution prediction of the Lower Paleozoic petroleum system in platform area of Tarim Basin [J]. Acta Petrolei Sinica, 2023, 44(9): 1459-1471.