Identification of Natural Gas Hydrates and Natural Gas Reservoirs Based on SMOTE and XGBoost

doi:10.3969/j.issn.1006-6535.2024.05.002

Abstract

Abstract: Natural gas hydrates identification and characterization are the key tasks throughout the exploration and development phase of marine energy resources.However,due to the complex nonlinear relationship between logging data and reservoirs,as well as the imbalance of logging data, traditional reservoir identification methods often show low accuracy,which severely limited the progress of energy exploration in the study area.To address the above issues,a composite method for reservoir identification is proposed.The improved SMOTE algorithm is used to increase the number of minority class reservoir samples and denoise the data,which effectively solves the issues of data imbalance.The XGBoost algorithm is then used to identify reservoirs.The results show that compared with traditional machine learning method,the RLSMOTE-XGB method has higher effectiveness and accuracy in reservoir identification.This method addresses the limitations of traditional machine learning methods in the case of imbalanced sample classes,increasing the reservoir identification accuracy from 66.7% to 86.4% and significantly improving the algorithm′s performance.This study can effectively improve the identification effect of natural gas hydrates and natural gas reservoirs,which is of great significance for achieving intelligent reservoir identification.

Key words: reservoir identification, SMOTE, machine learning, RLSMOTE-XGB, outlier detection algorithm

CLC Number:

TE348

Du Ruishan, Huang Yupeng, Fu Xiaofei, Meng Lingdong, Zhang Yi'nan, Jin Mingyang, Cai Hongbo. Identification of Natural Gas Hydrates and Natural Gas Reservoirs Based on SMOTE and XGBoost[J]. Special Oil & Gas Reservoirs, 2024, 31(5): 11-19.

References

[1] 裴发根,方慧,裴亮,等.天然气水合物电磁勘探研究进展[J].地球物理学进展,2020,35(2):775-785.
PEI Fagen,FANG Hui,PEI Liang,et al.Advances in electromagnetic exploration research of gas hydrate[J].Progress in Geophysics,2020,35(2):775-785.
[2] 魏纳,白睿玲,周守为,等.碳达峰目标下中国深海天然气水合物开发战略[J].天然气工业,2022,42(2):156-165.
WEI Na,BAI Ruiling,ZHOU Shouwei,et al.China′s deepwater gas hydrate development strategies under the goal of carbon peak[J].Natural Gas Industry,2022,42(2):156-165.
[3] REN J,CHENG C,XIONG P,et al.Sand-rich gas hydrate and shallow gas systems in the Qiongdongnan Basin, northern South China Sea[J].Journal of Petroleum Science and Engineering,2022,215:110630.
[4] 周守为,李清平,朱军龙,等.中国南海天然气水合物开发面临的挑战与思考[J].天然气工业,2023,43(11):152-163.
ZHOU Shouwei,LI Qingping,ZHU Junlong,et al.Challenges and considerations for the development of natural gas hydrates in South China Sea[J].Natural Gas Industry,2023,43(11):152-163.
[5] 韩博华,王飞,刘倩茹,等.测井储层分类评价方法研究进展综述[J].地球物理学进展,2021,36(5):1966-1974.
HAN Bohua,WANG Fei,LIU Qianru,et al.Review of research progress on evaluation of logging reservoir classification methods[J].Progress in Geophysics,2021,36(5):1966-1974.
[6] 程超,李培彦,陈雁,等.基于机器学习的储层测井评价研究进展[J].地球物理学进展,2022,37(1):164-177.
CHENG Chao,LI Peiyan,CHEN Yan,et al.Research progress of reservoir logging evaluation based on machine learning[J].Progress in Geophysics,2022,37(1):164-177.
[7] 赵军,吴博深,武延亮,等.深层致密砂岩气藏有效储层的分类评价方法[J].西南石油大学学报(自然科学版),2022,44(2):31-39.
ZHAO Jun,WU Boshen,WU Yanliang,et al.Classification and evaluation of effective reservoirs in deep tight sandstone gas reservoirsin[J].Journal of Southwest Petroleum University(Science & Technology Edition),2022,44(2):31-39.
[8] 李春雷,曹小朋,张林凤,等.基于机器学习算法的水驱储层相渗曲线仿真预测[J].油气地质与采收率,2022,29(6):138-142.
LI Chunlei,CAO Xiaopeng,ZHANG Linfeng,et al.Simulation and prediction of water-flooding reservoir relative permeability curve based on machine learning[J].Petroleum Geology and Recovery Efficiency,2022,29(6):138-142.
[9] VAFERI B,ESLAMLOUEYAN R,AYATOLLAHI S.Automatic recognition of oil reservoir models from well testing data by using multi-layer perceptron networks[J].Journal of Petroleum Science and Engineering,2011,77(3/4):254-262.
[10] GENG Z,HU X,DING N,et al.A pattern recognition modeling approach based on the intelligent ensemble classifier: application to identification and appraisal of water-flooded layers[J].Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering,2019,233(7):737-750.
[11] MOUSSA T,ELKATATNY S,MAHMOUD M,et al.Development of new permeability formulation from well log data using artificial intelligence approaches[J].Journal of Energy Resources Technology,2018,140(7):72903.
[12] 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 lithology of volcanic reservoirs based on machine learning[J].Special Oil & Gas Reservoirs,2022,29(1):38-45.
[13] 韩珊,车明光,苏旺,等.四川盆地威远区块页岩气单井产量预测方法及应用[J].特种油气藏,2022,29(6):141-149.
HAN Shan,CHE Mingguang,SU Wang,et al.Prediction method and application of single shale gas well production in Weiyuan Block,Sichuan Basin[J].Special Oil & Gas Reservoirs,2022,29(6):141-149.
[14] DENG C,PAN H,FANG S,et al.Support vector machine as an alternative method for lithology classification of crystalline rocks[J].Journal of Geophysics and Engineering,2017,14(2):341-349.
[15] PRADO E M G,DE SOUZA FILHO C R,CARRANZA E J M,et al.Modeling of Cu-Au prospectivity in the Carajás mineral province (Brazil) through machine learning:dealing with imbalanced training data[J].Ore Geology Reviews,2020,124:103611.
[16] 路允乾,孟大江,文鹏飞,等.琼东南盆地北部天然气水合物重点矿体预测及定量评价[J].非常规油气,2023,10(6):18-26.
LU Yunqian,MENG Dajiang,WEN Pengfei,et al.Prediction and quantitative evaluation of key ore bodies of natural gas hydrate in northern Qiongdongnan Basin[J].Unconventional Oil & Gas,2023,10(6):18-26.
[17] QIN X,LU J,LU H,et al.Coexistence of natural gas hydrate, free gas and water in the gas hydrate system in the Shenhu Area, South China Sea[J].China Geology,2020,3(2):210-220.
[18] 马通,祝鹏,陈鸣,等.琼东南盆地天然气水合物储层参数测井评价及分析[J].断块油气田,2023,30(2):254-260.
MA Tong,ZHU Peng,CHEN Ming,et al.Logging evaluation and analysis of reservoir parameter for natural gas hydrate in Qiongdongnan Basin[J].Fault-Block Oil & Gas Field,2023,30(2):254-260.
[19] 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 and Recovery Efficiency,2023,30(1):76-85.
[20] 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 and Recovery Efficiency,2022,29(1):175-180.
[21] CHAWLA N V,BOWYER K W,HALL L O,et al.SMOTE: synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2002,16(1):321-357.
[22] FAHRUDIN T,BULIALI J L,FATICHAH C.Enhancing the performance of smote algorithm by using attribute weighting scheme and new selective sampling method for imbalanced data set[J].International Journal of Innovative Computing, Information and Control,2019,15(2):423-444.
[23] TU B, ZHOU C, KUANG W,et al.Hyperspectral imagery noisy label detection by spectral angle local outlier factor[J].IEEE Geoscience and Remote Sensing Letters,2018,15(9):1417-1421.
[24] ZHU Q, FENG J, HUANG J.Natural neighbor:a self-adaptive neighborhood method without parameter K[J].Pattern Recognition Letters,2016,100(80):30-36.
[25] HOSSIN M,SULAIMAN M N.A review on evaluation metrics for data classification evaluations[J].International Journal of Data Mining & Knowledge Management Process,2015,5(2):1-11.
[26] 黄时卓,李芳,宋鹏,等.琼东南盆地超深水浅部气藏地球物理识别技术[J].地球科学,2024,49(1):313-323.
HUANG Shizhuo,LI Fang,SONG Peng,et al.Geophysical identification technology of ultra deep water and shallow gas reservoirs in Qiongdongnan Basin[J].Earth Science,2024,49(1):313-323.