Semi-Supervised Interlayer Identification Method Based on Self-Encoder

doi:10.3969/j.issn.1006-6535.2021.01.012

Abstract

Abstract: In order to solve the problems such as few interlayer data calibrated by core and unbalanced distribution of interlayers and sandstone samples, the deep self-encoder and semi-supervised learning method were used to calculate the abnormal scores and give the classification confidence to the abnormal scores. According to the classification confidence, the classification results of the interlayers were obtained, and the model was updated. The research results show that the deep self-encoder model using the update algorithm is effective in the interlayer identification, and the comprehensive classification accuracy reaches 85.00%. In addition, compared with other classification algorithms, the optimal model of AE7&UP has the highest F1_score (84.15%), indicating that the identification effect of the model is good and balanced. The research results are of great significance to reconstruct the cognition system of underground fluids.

Key words: interlayer identification, self-encoder, deep learning, semi-supervision

CLC Number:

TE122.1

Chen Yan, Jiao Shixiang, Cheng Chao, Huang Cheng, Jiang Yuqiang. Semi-Supervised Interlayer Identification Method Based on Self-Encoder[J]. Special Oil & Gas Reservoirs, 2021, 28(1): 86-91.

References

[1] 张斌,朱光有,苏劲,等.塔北隆起西部东河塘油气来源及分布[J].地学前缘,2012,19(4):276-283.
ZHANG Bin,ZHU Guangyou,SU Jin,et al.Origin and distribution of hydrocarbon in Donghetang Oifield,west Tabei Uplift,Tarim Basin[J].Earth Science Frontiers,2012,19(4):276-283.
[2] 李维禄,徐怀民,王超,等.基于动、静模式约束的隔、夹层空间分布综合预测——以塔里木盆地东河塘油田井区为例[J].西北大学学报(自然科学版),2016,46(6):877-886.
LI Weilu,XU Huaimin,WANG Chao,et al.Spatial distribution prediction of interlayers based on dynamic evaluation:a case of Donghetang sandstone in Donghetang Oil Field,Tarim Basin[J].Journal of Northwest University(Natural Science Edition),2016,46(6):877-886.
[3] 邓亚,郭睿,田中元,等.碳酸盐岩储集层隔夹层地质特征及成因——以伊拉克西古尔纳油田白垩系Mishrif组为例[J].石油勘探与开发,2016,43(1):136-144.
DENG Ya,GUO Rui,TIAN Zhongyuan,et al.Geologic features and genesis of the barriers and intercalations in carbonates:a case study of the Cretaceous Mishrif Formation,West Qurna Oil Field,Iraq[J].Petroleum Exploration and Development,2016,43(1):136-144.
[4] 印森林,吴胜和,冯文杰,等.冲积扇储集层内部隔夹层样式——以克拉玛依油田一中区克下组为例[J].石油勘探与开发,2013,40(6):757-763.
YIN Senlin,WU Shenghe,FENG Wenjie,et al.Patterns of inter-layers in the alluvial fan reservoirs:a case study on Triassic Lower Karamay Formation,Yizhong Area,Karamay Oilfield,NW China[J].Petroleum Exploration and Development,2013,40(6):757-763.
[5] 杜全伟,王维斌,刘志军,等.辽河西部凹陷大凌河油层隔夹层特征[J].特种油气藏,2015,22(3):74-76,154.
DU Quanwei,WANG Weibin,LIU Zhijun,et al.Characteristics of the intercalations in Dalinghe reservoir of the western sag,Liaohe Basin[J].Special Oil & Gas Reservoirs,2015,22(3):74-76,154.
[6] 马成龙.特厚层稠油油藏隔夹层识别研究[J].特种油气藏,2018,25(2):111-115.
MA Chenglong.Interlayer identification in ultra-thick heavy oil reservoir[J].Special Oil & Gas Reservoirs,2018,25(2):111-115.
[7] 孙天建,穆龙新,赵国良.砂质辫状河储集层隔夹层类型及其表征方法——以苏丹穆格莱特盆地Hegli油田为例[J].石油勘探与开发,2014,41(1):112-120.
SUN Tianjian,MU Longxin,ZHAO Guoliang.Classification and characterization of barrier-intercalation in sandy braided river reservoirs:taking Hegli Oilfield of Muglad Basin in Sudan as an example[J].Petroleum Exploration and Development,2014,41(1):112-120.
[8] 周学慧,丁文龙,昌伦杰,等.“三端员定型”法识别滨岸相砂岩储层隔夹层:以塔里木盆地哈得逊油田东河砂岩为例[J].地学前缘,2017,24(5):328-338.
ZHOU Xuehui,DING Wenlong,CHANG Lunjie,et al.Three-end-number diagram of classification to identify the interlayers of sandstone reservoir in littoral facies: a case from Carboniferous Donghe sandstone in Hade Oil Field,Tarim Basin,NW China[J].Earth Science Frontiers,2017,24(5):328-338.
[9] 周国文,谭成仟,郑小武,等.H油田隔夹层测井识别方法研究[J].石油物探,2006,45(5):542-545.
ZHOU Guowen,TAN Chengqian,ZHENG Xiaowu,et al.Research on recognition ofbarrier/interbed via logging in H Oilfield[J].Geophysical Prospecting for Petroleum,2006,45(5):542-545.
[10] 张吉,张烈辉,胡书勇,等.陆相碎屑岩储层隔夹层成因、特征及其识别[J].测井技术,2003,22(4):221-224.
ZHANG Ji,ZHANG Liehui,HU Shuyong,et al.The genesis and characteristics and identification of intercalations in non-marine reservoir with clastic rock[J].Well Logging Technology,2003,22(4):221-224.
[11] 谷建伟,周梅,李志涛,等.基于数据挖掘的长短期记忆网络模型油井产量预测方法[J].特种油气藏,2019,26(2):77-81,131.
GU Jianwei,ZHOU Mei,LI Zhitao,et al.Oil well production forecast with long-short term memory network model based on data mining[J].Special Oil & Gas Reservoirs,2019,26(2):77-81,131.
[12] 李克文,周广悦,路慎强,等.一种基于机器学习的有利区评价新方法[J].特种油气藏,2019,26(3):7-11.
LI Kewen,ZHOU Guangyue,LU Shenqiang,et al.A new method for favorable zone evaluation based on machine learning[J].Special Oil & Gas Reservoirs,2019,26(3):7-11.
[13] 张东晓,陈云天,孟晋.基于循环神经网络的测井曲线生成方法[J].石油勘探与开发,2018,45(4):598-607.
ZHANG Dongxiao,CHEN Yuntian,MENG Jin.Synthetic well logs generation via recurrent neural networks[J].Petroleum Exploration and Development,2018,45(4):598-607.
[14] 瞿子易,罗鑫,谢润成,等.小波神经网络在隔夹层研究中的应用[J].石油天然气学报,2009,31(4):265-268.
QU Ziyi,LUO Xin,XIE Runcheng,et al.Application of WNN in the studies of interbeds[J].Journal of Oil and Gas Technology,2009,31(4):265-268.
[15] SHAHSHAHANI B M,LANDGREBE D A.The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon[J].IEEE Transactions of Geoscience & Remote Sensing,1994,32(5):1087-1095.
[16] YANG Zhimin ,CAO Xinxia,SHAO Yuanhai.Weak fuzzy support vector machine based on credibility measure[J].Journal of Convergence Information Technology,2012,7(10):322-329.
[17] VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J].Journal of Machine Learning Research,2010,11(12):3371-3408.
[18] KIM K H,BAE J W.Amplification methods bias metagenomic libraries of uncultured single-stranded and double-stranded DNA viruses[J].Applied and Environmental Microbiology,2011,77(21):7663-7668.
[19] FAN Z,BI D,HE L,et al.Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder[J].Neurocomputing,2017,243:12-20.
[20] SHIN M,MUN S,HAN D K,et al.New generalized sidelobe canceller with denoising auto-encoder for improved speech enhancement[J].Ice Transactions on Fundamentals of Electronics Communications & Computerences,2017,100(12):3038-3040.
[21] WEN L,GAO L,LI X.A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,2019,49(1):136-144.
[22] 孙文珺,邵思羽,严如强.基于稀疏自动编码深度神经网络的感应电动机故障诊断[J].机械工程学报,2016,52(9):65-71.
SUN Wenjun,SHAO Siyu,YAN Ruqiang.Induction motor fault diagnosis based on deep neural network of sparse auto-encoder[J].Journal of Mechanical Engineering,2016,52(9):65-71.
[23] DU B,XIONG W,WU J,et al.Stacked convolutional denoising auto-encoders for feature representation[J].IEEE Transactions on Cybernetics,2017,47(4):1017-1027.