TOC prediction model for muddy source rocks based on convolutional neural network (CNN): a case study of the Hangjinqi area of the Ordos Basin

WANG Huijun; ZHAO Guiping; LI Liang; ZHANG Wei; QI Rong; LIU Jun

doi:10.7523/j.issn.2095-6134.2020.01.012

Journal of University of Chinese Academy of Sciences >

2020 , Vol. 37 >Issue 1: 103 - 112

DOI: https://doi.org/10.7523/j.issn.2095-6134.2020.01.012

Research Articles

TOC prediction model for muddy source rocks based on convolutional neural network (CNN): a case study of the Hangjinqi area of the Ordos Basin

WANG Huijun ,
ZHAO Guiping ,
LI Liang ,
ZHANG Wei ,
QI Rong ,
LIU Jun

Expand

1 College of Earth and Planetary Science, University of Chinese Academy of Sciences, Beijing 100049, China;
2 Key Laboratory of Computational Geodynamics of Chinese Academy of Sciences, Beijing 100049, China;
3 Geoscience Research Institute of North China Company, SINOPEC, Zhengzhou 450006, China;
4 Well Logging Company of North China Petroleum Engineering Company, SINOPEC, Zhengzhou 450006, China

Received date: 2018-07-23

Revised date: 2018-11-29

Online published: 2020-01-15

Fold

Abstract

Total organic carbon (TOC) is a significant factor for oil and gas exploration and development. For determining TOC, previous researchers mainly employed ΔlogR and back propagation artificial neural network (BP). However, ΔlogR has a low coefficient of the determination of the calculated TOC compared to the core measured data, while BP is easily trapped into a local optimum. To address these challenges, we propose a new method based on convolutional neural network (CNN) to calculate TOC. In this work, the argillaceous source rocks in the Hangjinqi area of the Ordos Basin were studied, and the effectiveness of the method was verified. The experimental verification showed that CNN could be used for TOC prediction of the source rocks and the prediction accuracy was higher than those of ΔlogR and BP neural network. CNN was used to predict the TOC values of the Shan 1 and Taiyuan mudstones of 108 wells. The TOC planar graphs were made in combination with the sedimentary microfacies. We found that the TOC values of the swamps in the southeast and central parts were higher and the TOC values of the distributary channels were generally lower. The TOC plane distribution well matched the sedimentary microfacies distribution, showing the feasibility of this prediction method.

Key words： muddy source rock; TOC content; well logging; convolutional neural network(CNN); BP neural network(BPNN)

Cite this article

WANG Huijun , ZHAO Guiping , LI Liang , ZHANG Wei , QI Rong , LIU Jun . TOC prediction model for muddy source rocks based on convolutional neural network (CNN): a case study of the Hangjinqi area of the Ordos Basin[J]. Journal of University of Chinese Academy of Sciences, 2020 , 37(1) : 103 -112 . DOI: 10.7523/j.issn.2095-6134.2020.01.012

References

[1] Passey Q R, Moretti F J, Kulla J B, et al. Practical model for organic richness from porosity and resistivity logs[J]. AAPG Bulletin, 1990, 74(12):1777-1794.
[2] 胡慧婷, 卢双舫, 刘超, 等. 测井资料计算源岩有机碳含量模型对比及分析[J]. 沉积学报, 2011, 29(6):1199-1205.
[3] 胡慧婷, 苏瑞, 刘超, 等. 广义ΔLgR技术预测陆相深层烃源岩有机碳含量方法及其应用[J]. 天然气地球科学, 2016, 27(1):149-155.
[4] 刘超. 测井资料评价烃源岩方法改进及作用[D]. 黑龙江大庆:东北石油大学, 2011.
[5] 刘超, 卢双舫, 薛海涛. 变系数ΔlogR方法及其在泥页岩有机质评价中的应用[J]. 地球物理学进展, 2014, 29(1):312-317.
[6] 朱光有, 金强, 张林晔. 用测井信息获取烃源岩的地球化学参数研究[J]. 测井技术, 2003, 27(2):104-109.
[7] 王攀, 彭苏萍, 杜文凤, 等. 基于测井参数的煤系烃源岩总有机碳含量预测模型[J]. 煤炭学报, 2017, 42(5):1266-1276.
[8] 郭龙, 陈践发, 苗忠英. 一种新的TOC含量拟合方法研究与应用[J]. 天然气地球科学, 2009, 20(6):951-956.
[9] Zhu Z, Wang G, Zhu G. The application of artificial neural network to the source rock's evaluation[J]. Progress in Geophysiscs, 2002, 17(1):137-140.
[10] Tan M, Song X, Yang X, et al. Support-vector-regression machine technology for total organic carbon content prediction from wireline logs in organic shale:a comparative study[J]. Journal of Natural Gas Science & Engineering, 2015, 26(1):792-802.
[11] Shi X, Wang J, Liu G, et al. Application of extreme learning machine and neural networks in total organic carbon content prediction in organic shale with wire line logs[J]. Journal of Natural Gas Science & Engineering, 2016, 33:687-702.
[12] Mahmoud A A A, Elkatatny S, Mahmoud M, et al. Determination of the total organic carbon (TOC) based on conventional well logs using artificial neural network[J]. International Journal of Coal Geology, 2017, 179:72-80.
[13] Bolandi V, Kadkhodaie A, Farzi R. Analyzing organic richness of source rocks from well log data by using SVM and ANN classifiers:a case study from the Kazhdumi formation, the Persian Gulf basin, offshore Iran[J]. Journal of Petroleum Science & Engineering, 2017, 151:224-234.
[14] Bakhtiar H A, Telmadarreie A, Shayesteh M, et al. Estimating total organic carbon content and source rock evaluation, applying ΔlogR and neural network methods:Ahwaz and Marun Oilfields, SW of Iran[J]. Petroleum Science and Technology, 2011, 29(16):1691-1704.
[15] Alizadeh B, Najjari S, Kadkhodaie-ilkhchi A. Artificial neural network modeling and cluster analysis for organic facies and burial history estimation using well log data:a case study of the South Pars Gas Field, Persian Gulf, Iran[J]. Computers & Geosciences, 2012, 45(4):261-269.
[16] Fu J, Zheng H, Mei T. Look closer to see better:Recurrent attention convolutional neural network for fine-grained image recognition[C]//CVPR. 2017:4476-4484.
[17] Karpathy A, Toderici G, Shetty S, et al. Large-scale video classification with convolutional neural networks[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2014:1725-1732.
[18] Abdel-hamid O, Mohamed A-r, Jiang H, et al. Convolutional neural networks for speech recognition[J]. IEEE ACM Transactions on audio, speech, and language processing, 2014, 22(10):1533-1545.
[19] Er M J, Zhang Y, Wang N, et al. Attention pooling-based convolutional neural network for sentence modelling[J]. Information Sciences, 2016, 373:388-403.
[20] Zhao D, Yang T, Ou W, et al. Autopilot design for unmanned surface vehicle based on CNN and ACO[J]. International Journal of Computers, Communications & Control, 2018, 13(3):429-439.
[21] 程国建, 郭文惠, 范鹏召. 基于卷积神经网络的岩石图像分类[J]. 西安石油大学学报(自然科学版), 2017, 32(4):116-122.
[22] 程国建, 岳清清. 卷积神经网络在岩石薄片图像检索中的应用初探[J]. 智能计算机与应用, 2018, 8(2):43-51.
[23] 段友祥, 李根田, 孙歧峰. 卷积神经网络在储层预测中的应用研究[J]. 通信学报, 2016, 37(s1):1-9.
[24] 纪雪. 基于多波束数据的海底底质及地形复杂度分类研究[D]. 山东青岛:国家海洋局第一海洋研究所, 2017.
[25] 曹林林, 李海涛, 韩颜顺,等. 卷积神经网络在高分遥感影像分类中的应用[J]. 测绘科学, 2016, 41(9):170-175.
[26] Wu X, Ni C, Liu Q, et al. Genetic types and source of the Upper Paleozoic tight gas in the Hangjinqi area, northern Ordos Basin, China[J]. Geofluids, 2017, 3:1-14.
[27] 杨俊杰, 裴锡古. 中国天然气地质学:第4卷:鄂尔多斯盆地[M]. 北京:石油工业出版社, 1996.
[28] 杨娅敏, 赵桂萍, 李良,等. 杭锦旗地区地层水特征研究及其油气地质意义[J]. 中国科学院大学学报, 2016, 33(4):519-527.
[29] He J, Ding W, Jiang Z, et al. Logging identification and characteristic analysis of the lacustrine organic-rich shale lithofacies:a case study from the Es3l shale in the Jiyang Depression, Bohai Bay Basin, Eastern China[J]. Journal of Petroleum Science and Engineering, 2016, 145:238-255.
[30] 王攀,梁明星. 煤系烃源岩测井响应特征及有机碳评价方法[J]. 物探与化探, 2016, 40(1):197-202.
[31] 殷瑞, 苏松志, 李绍滋. 一种卷积神经网络的图像矩正则化策略[J]. 智能系统学报, 2016, 11(1):43-48.
[32] 刘万军, 梁雪剑, 曲海成. 不同池化模型的卷积神经网络学习性能研究[J]. 中国图象图形学报, 2016, 21(9):1178-1190.
[33] 庞雄奇, 李倩文, 陈践发, 等. 含油气盆地深部高过成熟烃源岩古TOC恢复方法及其应用[J]. 古地理学报, 2014, 16(6):769-789.

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References