Prediction model of coalbed methane content based on well logging parameter optimization

Authors

CHEN Tao, College of Physics and Petroleum Resources, Yangtze University, Wuhan 430100, China; Key Laboratory of Exploration Technologies for Oil and Gas Resources(Yangtze University), Ministry of Education, Wuhan 430100, China
ZHANG Zhansong, College of Physics and Petroleum Resources, Yangtze University, Wuhan 430100, China; Key Laboratory of Exploration Technologies for Oil and Gas Resources(Yangtze University), Ministry of Education, Wuhan 430100, ChinaFollow
ZHOU Xueqing, College of Physics and Petroleum Resources, Yangtze University, Wuhan 430100, China; Key Laboratory of Exploration Technologies for Oil and Gas Resources(Yangtze University), Ministry of Education, Wuhan 430100, China
GUO Jianhong, College of Physics and Petroleum Resources, Yangtze University, Wuhan 430100, China; Key Laboratory of Exploration Technologies for Oil and Gas Resources(Yangtze University), Ministry of Education, Wuhan 430100, China
XIAO Hang, College of Physics and Petroleum Resources, Yangtze University, Wuhan 430100, China; Key Laboratory of Exploration Technologies for Oil and Gas Resources(Yangtze University), Ministry of Education, Wuhan 430100, China
TAN Chenyang, College of Physics and Petroleum Resources, Yangtze University, Wuhan 430100, China; Key Laboratory of Exploration Technologies for Oil and Gas Resources(Yangtze University), Ministry of Education, Wuhan 430100, China
QIN Ruibao, CNOOC Research Institute, Beijing 100027, China
YU Jie, CNOOC Research Institute, Beijing 100027, China

Abstract

With the development of coalbed methane(CBM) exploration, higher accuracy of CBM content prediction is required. Based on the response characteristics of CBM logging, the correlation between logging parameters and gas content is analyzed, and the optimization strategy of logging parameters by combining MIV technology with LSSVM is proposed. The optimal logging parameters are selected as the input independent variables of network modeling, and the core parameters of LSSVM(Least Squares Support Vector Machine) network are optimized by particle swarm optimization. Finally, a set of MIV-PSO-LSSVM model suitable for CBM content prediction is constructed. The prediction performances of LSSVM, PSO-LSSVM, MIV-LSSVM, MIV-PSO-LSSVM and traditional multiple regression method are compared and analyzed respectively. The results show that the prediction accuracy of LSSVM model optimized by PSO is increased, and the modeling performance of neural network is improved significantly with MIV method to optimize logging parameters. MIV-PSO-LSSVM model could realize high-precision prediction of CBM content, providing new technical support for CBM exploration and reservoir evaluation. And the modeling strategy of this research can be widely used in other ML(machine learning) modeling research fields.

Keywords

coalbed methane(CBM), gas content, MIV(Mean Impact Value), LSSVM(Least Squares Support Vector Machine), PSO(Particle Swarm Optimization), logging curve

DOI

10.3969/j.issn.1001-1986.2021.03.029

Recommended Citation

CHEN Tao, ZHANG Zhansong, ZHOU Xueqing, et al. (2021) "Prediction model of coalbed methane content based on well logging parameter optimization," Coal Geology & Exploration: Vol. 49: Iss. 3, Article 30.
DOI: 10.3969/j.issn.1001-1986.2021.03.029
Available at: https://cge.researchcommons.org/journal/vol49/iss3/30

Reference

[1] HAWKINS J M,SCHRAUFNAGEL R A,OLSZEWSKI A J. Estimating coalbed gas content and sorption isotherm using well log data[C]//SPE24905,1992:491-501.

[2] 侯颉,邹长春,杨玉卿,等. 测井解释中煤层含气量评价方法对比研究[J]. 煤炭科学技术,2015,43(12):157-161. HOU Jie,ZOU Changchun,YANG Yuqing,et al. Comparison study on evaluation methods of coalbed methane gas content with logging interpretation[J]. Coal Science and Technology,2015,43(12):157-161.

[3] 董红,侯俊胜,李能根,等. 煤层煤质和含气量的测井评价方法及其应用[J]. 物探与化探,2001,25(2):138-143. DONG Hong,HOU Junsheng,LI Nenggen,et al. The logging evaluation method for coal quality and methane[J]. Geophysical and Geochemical Exploration,2001,25(2):138-143.

[4] 刘效贤,李承华. 测井评价煤层气储层的方法探讨[J]. 中国煤炭地质,2008,20(12):1-3. LIU Xiaoxian,LI Chenghua. Probe into CBM reservoir evaluation through well logging[J]. Coal Geology of China,2008,20(12):1-3.

[5] 葛祥,何传亮,董震. 基于动态吸附模型的煤岩吸附气含量测井计算新方法[J]. 测井技术,2014,38(6):740-744. GE Xiang,HE Chuanliang,DONG Zhen. New method to calculate adsorbed gas content of coalbed based on the dynamic adsorption model[J]. Well Logging Technology,2014,38(6):740-744.

[6] 刘荣芳,王建功,刘文华,等. 基于煤岩结构的煤层含气量测井评价方法[J]. 中国煤层气,2014,11(4):22-25. LIU Rongfang,WANG Jiangong,LIU Wenhua,et al. CBM logging evaluation method based on coal seam structure[J]. China Coalbed Methane,2014,11(4):22-25.

[7] 金泽亮,薛海飞,高海滨,等. 煤层气储层测井评价技术及应用[J]. 煤田地质与勘探,2013,41(2):42-45. JIN Zeliang,XUE Haifei,GAO Haibin,et al. Technology for evaluation of CBM reservoir logging and its application[J]. Coal Geology & Exploration,2013,41(2):42-45.

[8] 李贵红,张泓,崔永君,等. 基于多元逐步回归分析的煤储层含气量预测模型:以沁水盆地为例[J]. 煤田地质与勘探,2005,33(3):22-25. LI Guihong,ZHANG Hong,CUI Yongjun,et al. A predictive model of gas content in coal reservoirs based on multiple stepwise regression analysis:A case study from Qinshui Basin[J]. Coal Geology & Exploration,2005,33(3):22-25.

[9] 吴东平,岳晓燕,吴春萍. 神经网络技术在煤层气测井评价中的应用[J]. 断块油气田,2000,7(5):48-49. WU Dongping,YUE Xiaoyan,WU Chunping. Evaluation of coalbed gas logging with nerve network[J]. Fault-Block Oil and Gas Field,2000,7(5):48-49.

[10] 孟召平,田永东,雷旸. 煤层含气量预测的BP神经网络模型与应用[J]. 中国矿业大学学报,2008,37(4):456-461. MENG Zhaoping,TIAN Yongdong,LEI Yang. Prediction models of coal bed gas content based on BP neural networks and its applications[J]. Journal of China University of Mining & Technology,2008,37(4):456-461.

[11] 孟召平,郭彦省,张纪星. 基于测井参数的煤层含气量预测模型与应用[J]. 煤炭科学技术,2014,42(6):25-30. MENG Zhaoping,GUO Yansheng,ZHANG Jixing. Application and prediction model of coalbed methane content based on logging parameters[J]. Coal Science and Technology,2014,42(6):25-30.

[12] 郭建宏,张占松,张超谟,等. 基于灰色系统与测井方法的煤层气含量预测及应用[J]. 物探与化探,2020,44(5):1190-1200. GUO Jianhong,ZHANG Zhansong,ZHANG Chaomo,et al. Prediction and application of coalbed methane content based on gray system and logging method[J]. Geophysical and Geochemical Exploration,2020,44(5):1190-1200.

[13] 刘爱华,傅雪海,王可新,等. 支持向量机预测煤层含气量[J]. 西安科技大学学报,2010,30(3):309-313. LIU Aihua,FU Xuehai,WANG Kexin,et al. Prediction of coalbed gas content based on support vector machine regression[J]. Journal of Xi'an University of Science and Technology,2010,30(3):309-313.

[14] 郭建宏,张占松,张超谟,等. 用地球物理测井资料预测煤层气含量:基于斜率关联度-随机森林方法的工作案例[J]. 物探与化探,2021,45(1):18-28. GUO Jianhong,ZHANG Zhansong,ZHANG Chaomo,et al. The exploration of predicting CBM content by geophysical logging data:A case study based on slope correlation random forest method[J]. Geophysical and Geochemical Exploration,2021,45(1):18-28.

[15] 贾承造,郑民,张永峰. 中国非常规油气资源与勘探开发前景[J]. 石油勘探与开发,2012,39(2):129-136. JIA Chengzao,ZHENG Min,ZHANG Yongfeng. Unconventional hydrocarbon resources in China and the prospect of exploration and development[J]. Petroleum Exploration and Development,2012,39(2):129-136.

[16] 黄兆辉,邹长春,杨玉卿,等. 沁水盆地南部TS地区煤层气储层测井评价方法[J]. 现代地质,2012,26(6):1275-1282. HUANG Zhaohui,ZOU Changchun,YANG Yuqing,et al. Coalbed methane reservoir evaluation from wireline logs in TS district,southern Qinshui Basin[J]. Geoscience,2012,26(6):1275-1282.

[17] VAPNIK V N. An overview of statistical learning theory[J]. IEEE Transactions on Neural Network,1999,10(5):988-999.

[18] WANG Pan,PENG Suping. A new scheme to improve the performance of artificial intelligence techniques for estimating total organic carbon from well logs[J]. Energies,2018,11(4):747.

[19] SUYKENS J A K,VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letters,1999,9(3):293-300.

[20] EBERHART R,KENNEDY J. A new optimizer using particle swarm theory[C]//IEEE. Proceeding of the IEEE 6th International Symposium on Micro Machine and Human Science. US:IEEE,1995:39-43.

[21] DOMBI G W,NANDI P,SAXE J M,et al. Prediction of rib fracture injury outcome by an artificial neural network[J]. The Journal of Trauma,1995,39(5):915-921.

[22] WANG Ziwei,YE Qiwang. Cancer informative gene identification based on MIV method of neural network[J]. Journal of Mathematics in Practice and Theory,2011,41(14):47-58.

[23] WANG Pan,PENG Suping,HE Taohua. A novel approach to total organic carbon content prediction in shale gas reservoirs with well logs data,Tonghua Basin,China[J]. Journal of Natural Gas Science and Engineering,2018,55:1-15.

[24] 周游,张广智,高刚,等. 核主成分分析法在测井浊积岩岩性识别中的应用[J]. 石油地球物理勘探,2019,54(3):667-675. ZHOU You,ZHANG Guangzhi,GAO Gang,et al. Application of kernel principal component analysis in well logging turbidite lithology identification[J]. Oil Geophysical Prospecting,2019,54(3):667-675.