Special Oil & Gas Reservoirs >

2024 , Vol. 31 >Issue 5: 41 - 49

DOI: https://doi.org/10.3969/j.issn.1006-6535.2024.05.005

Geologic Exploration

Volcanic Rock Identification Method Based on Machine Learning and Its Application

  • Zhu Bohan ,
  • Shan Xuanlong ,
  • Yi Jian ,
  • Shi Yunqian ,
  • Guo Jiannan ,
  • Liu Pengcheng ,
  • Wang Shuyang ,
  • Li Ang
Expand
  • Jilin University, Changchun, Jilin 130012, China

Received date: 2023-10-28

  Revised date: 2024-07-04

  Online published: 2024-12-24

Fold

Abstract

In the southern part of Songliao Basin, Chaganhua Area, the lithology of the Huoshiling Formation volcanic rocks is complex and variable. Traditional methods such as two-dimensional intersection and step-by-step classification based on conventional well logging data are difficult to accurately identify the lithology of volcanic rocks. To address the issues, a proposal is developed to use machine learning algorithms for intelligent identification of volcanic rock lithology. By observing sample cores and thin section analysis, the lithology of volcanic rocks in the sampled section is determined. The logging data set of the coring section is divided into training set and test set. The training set is used to match the object function, and the test set is brought into the model to predict results, and use integrate models with ensemble learning to conduct blind well prediction.The fusion model establishes a quantitative mathematical relationship between the characteristics of each well log curve, integrates the characteristics of multiple machine learning, and improves the learning efficiency of the model based on accurate lithology data set labels.The results show that the prediction accuracy of the integrate model for blind wells achieves 95.10%. The model has wide applicability, which can accurately identify and predict the lithology of volcanic rocks. This study can provide support for the intelligent exploration of volcanic rock oil and gas.

Key words： volcanic rock; lithology; machine learning; integrated learning; GBDT gradient decision tree; Songliao Basin

Cite this article

Zhu Bohan , Shan Xuanlong , Yi Jian , Shi Yunqian , Guo Jiannan , Liu Pengcheng , Wang Shuyang , Li Ang . Volcanic Rock Identification Method Based on Machine Learning and Its Application[J]. Special Oil & Gas Reservoirs, 2024 , 31(5) : 41 -49 . DOI: 10.3969/j.issn.1006-6535.2024.05.005

References

[1] 牛花朋,王贵文,鲜本忠,等.深层火山碎屑熔岩形成机理及其指相意义研究:以松辽盆地庆深气田为例[J].地学前缘,2019,26(6):281-288.
NIU Huapeng,WANG Guiwen,XIAN Benzhong,et al.The formation mechanism of pyroclastic lava and its significance for the identification of volcanic rock faces:a case study from Qingshen Gasfield,Songliao Basin[J].Earth Science Frontiers,2019,26(6):281-288.
[2] 石新朴,覃建强,丁艳雪,等.准噶尔盆地滴南凸起火山岩气藏成藏主控因素与成藏模式[J].天然气地球科学,2018,29(12):1706-1714.
SHI Xinpu,QIN Jianqiang,DING Yanxue,et al.Models and controlling factors of volcanic gas reservoirs forming in Dinan Salient in Junggar Basin[J].Natural Gas Geoscience,2018,29(12):1706-1714.
[3] 赵静,白连德.松辽盆地南部火山岩优质储层主控因素[J].特种油气藏,2016,23(3):52-56,153.
ZHAO Jing,BAI Liande.Main controlling factors of high-quality volcanic reservoir in southern Songliao Basin[J].Special Oil & Gas Reservoirs,2016,23(3):52-56,153.
[4] 叶涛,韦阿娟,邓辉,等.基于常规测井资料的火山岩岩性识别方法研究——以渤海海域中生界为例[J].地球物理学进展,2017,32(4):1842-1848.
YE Tao,WEI Ajuan,DENG Hui, et al.Study on volcanic lithology identification methods based on the data of conventional well logging data: a case from Mesozoic volcanic rocks in Bohai Bay Area[J].Progress in Geophysics,2017,32(4):1842-1848.
[5] 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1):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.
[6] 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.
ZHU Yixiang,SHI Guangren.Identification of lithologic characteristics of volcanic rocks by support vector machine[J].Acta Petrolei Sinica,2013,34(2):312-322.
[7] 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 Chang 7 Reservoir in Heshui Area by KNN algorithm[J].Well Logging Technology,2020,44(2):182-185.
[8] 洪一鸣,王璞珺,李瑞磊,等.基于常规测井数据的火山岩岩性神经网络识别:以松辽盆地南部长岭断陷为例[J].世界地质,2021,40(2):408-418.
HONG Yiming,WANG Pujun,LI Ruilei,et al.Neural network recognition of volcanic rock lithology based on conventional logging data:a case study of Changling fault depression,southern Songliao Basin[J].Global Geology,2021,40(2):408-418.
[9] 魏周城.准噶尔盆地金龙2井区火山岩岩性及裂缝识别与预测[D].北京:中国石油大学(北京),2019.
WEI Zhoucheng.Identification and prediction of volcanic rock lithology and fracture in the area of Jinlong-2 Well,Junggar Basin[D].Beijing:China University of Petroleum(Beijing),2019.
[10] 赵耀,潘虹,骆飞飞,等.准噶尔盆地红车断裂带石炭系火山岩储层特征及质量控制因素[J].石油与天然气地质,2023,44(5):1129-1140.
ZHAO Yao,PAN Hong,LUO Feifei,et al.Characteristics and quality determinants of Carboniferous volcanic reservoirs in the Hongche Fault Zone,Junggar Basin[J].Oil & Gas Geology,2023,44(5):1129-1140.
[11] 唐华风,边伟华,王璞珺,等.盆地火山岩相分类和模式[J].吉林大学学报(地球科学版),2023,53(6):1651-1671.
TANG Huafeng,BIAN Weihua,WANG Pujun,et al.Classification and model of volcanic facies in the basin[J].Journal of Jilin University (Earth Science Edition),2023,53(6):1651-1671.
[12] 李宗浩,侯磊,李卉,等.准噶尔盆地石西凸起晚石炭世火山岩储层发育影响因素[J].油气地质与采收率,2023,30(4):33-45.
LI Zonghao,HOU Lei,LI Hui,et al.Influencing factors of late Carboniferous volcanic reservoir development in Shixi Uplift,Junggar Basin[J].Petroleum Geology & Recovery Efficiency,2023,30(4):33-45.
[13] 王韬,徐倩,李永军,等.车排子油田南部火山岩地质时代及成因[J].新疆石油地质,2022,43(2):160-168.
WANG Tao,XU Qian,LI Yongjun,et al.Geological age and petrogenesis of volcanic rocks in southern Chepaizi Oilfield[J]. Xinjiang Petroleum Geology,2022,43(2):160-168.
[14] 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.
YAN Shicui.Prediction method of sandstone lithology based on optimized machine learning algorithms and attribute features[J].Petroleum Geology & Recovery Efficiency,2022,29(1):98-106.
[15] 李素华,贾霍甫,胡昊,等.四川盆地井研地区火山岩岩相类型及储层分布[J].特种油气藏,2022,29(6):39-46.
LI Suhua,JIA Huofu,HU Hao,et al.Lithofacies types and reservoir distribution of volcanic rocks in Jingyan Area,Sichuan Basin[J].Special Oil & Gas Reservoirs,2022,29(6):39-46.
[16] 孙岿.基于改进KNN算法的潜山复杂岩性测井识别方法[J].特种油气藏,2022,29(3): 18-27.
SUN Kui.A logging identification method of buried hill complex lithology based on improved KNN algorithm[J].Special Oil & Gas Reservoirs,2022,29(3):18-27.
[17] 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.
MU 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.
[18] 朱明永,李炳谦,付翰泽,等.基于多源数据协同的SVM岩性分类研究——以江尕勒萨依地区为例[J].铀矿地质,2020,36(4):288-292.
ZHU Mingyong,LI Bingqian,FU Hanze,et al.SVM lithological classification based on multi-source data collaboration:a case study in Jianggalesayi Area[J].Uranium Geology,2020,36(4):288-292.
[19] 姜世一,孙盼科,张林,等.基于径向基—多层感知器神经网络联合的复杂岩相智能识别与表征[J].天然气工业,2022,42(9):47-62.
JIANG Shiyi,SUN Panke,ZHANG Lin,et al.Intelligent identification and characterization of complex lithofacies based on radial basis-multilayer perception neural network joint model[J].Natural Gas Industry,2022,42(9):47-62.
[20] 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.
[21] 翟亮.基于XGBoost 算法的吸水剖面预测方法研究与应用[J].油气地质与采收率,2022,29(1):175-180.
ZHAI Liang.XGBoost-based water injection profile prediction method and its application[J].Petroleum Geology & Recovery Efficiency,2022,29(1):175-180.
[22] 彭英,李克文,朱应科,等.基于FL-XGBoost算法的砂泥岩识别方法——以胜利油田牛庄地区为例[J].油气地质与采收率,2023,30(1):76-85.
PENG Ying,LI Kewen,ZHU Yingke,et al.FL-XGBoost algorithm-based method for identifying sandstone and mudstone:a case study of Niuzhuang Area in Shengli Oilfield[J].Petroleum Geology & Recovery Efficiency,2023,30(1):76-85.
[23] 韩玉娇.基于AdaBoost机器学习算法的大牛地气田储层流体智能识别[J].石油钻探技术,2022,50(1):112-118.
HAN Yujiao.Intelligent fluid identification based on the AdaBoost machine learning algorithm for reservoirs in Daniudi Gas Field[J].Petroleum Drilling Techniques,2022,50(1):112-118.
[24] 谷宇峰,张道勇,鲍志东,等.GBDT识别致密砂岩储层岩性[J].地球物理学进展,2021,36(5):1956-1965.
GU Yufeng,ZHANG Daoyong,BAO Zhidong,et al.Lithology prediction of tight sandstone reservoirs using GBDT[J].Progress in Geophysics,2021,36(5):1956-1965.
[25] 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 & Recovery Efficiency,2023,30(6):13-21.
[26] 付君豪,陈再贺,付宪,等.利用随机森林算法预测束鹿凹陷束21井区馆陶组储层砂地比[J].大庆石油地质与开发,2023,42(6):34-41.
FU Junhao,CHEN Zaihe,FU Xian,et al. Prediction of sandstone-strata thickness ratio of Guantao Formation reser-voir in Shu 21 Well Area of Shulu Sag via random forest algorithm[J].Petroleum Geology & Oilfield Development in Daqing,2023,42(6):34-41.
[27] 马骊.随机森林算法的优化改进研究[D].广州:暨南大学,2016.
MA Li.Research on optimization and improvement of random forest algorithm[D].Guangzhou:Jinan University,2016.
[28] 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 & Recovery Efficiency,2022,29(1):21-29.
[29] 刘凯,邹正银,王志章,等.基于机器学习的火山岩岩性智能识别及预测[J].特种油气藏,2022,29(1):38-45.
LIU Kai,ZOU Zhengyin,WANG Zhizhang,et al.Intelligent identification and prediction of volcanic lithology based on machine learning[J].Special Oil & Gas Reservoirs,2022,29(1):38-45.
[30] 单玄龙,牟汉生,刘玉虎,等.湖盆水下喷发火山岩相类型、特征与储集意义——以松辽盆地南部查干花地区白垩系为例[J].石油勘探与开发,2023,50(4):719-730.
SHAN Xuanlong,MU Hansheng,LIU Yuhu,et al.Subaqueous volcanic eruptive facies,facies model and its reservoir significance in a continental lacustrine basin:a case from the Cretaceous in Chaganhua Area of southern Songliao Basin,NE China[J].Petroleum Exploration and Development,2023,50(4):719-730.
[31] 石云倩.松辽盆地南部白垩系火石岭组火山岩特征与喷发就位环境及其储层发育模式[D].长春:吉林大学,2023.
SHI Yunqian.Volcanic rock characteristics, eruption environment and reservoir development model of Cretaceous Huoshiling Formation in southern Songliao Basin[D].Changchun:Jilin University,2023.
[32] 杨双,李忠博,闫相宾,等.火山岩圈闭识别描述方法及其应用[J]. 石油实验地质, 2021, 43(3): 540-548.
YANG Shuang,LI Zhongbo,YAN Xiangbin, et al.Method of identifying and characterizing of volcanic traps and its application[J].Petroleum Geology & Experiment,2021,43(3):540-548.
Options
Outlines

/

〈 〉