Please wait a minute...
E-mail Alert Rss
 
物探与化探  2021, Vol. 45 Issue (3): 569-575    DOI: 10.11720/wtyht.2021.1507
  清洁能源勘探 本期目录 | 过刊浏览 | 高级检索 |
深度学习在南川页岩气含气量预测中的应用
张勇1(), 马晓东1, 李彦婧1, 蔡景顺2
1.中国石化华东油气分公司 勘探开发研究院,江苏 南京 210005
2.四川宝石花鑫盛油气运营服务有限公司,四川 成都 610000
The application of deep learning to the shale gas content prediction in Nanchuan(South Sichuan)
ZHANG Yong1(), MA Xiao-Dong1, LI Yan-Jing1, CAI Jing-Shun2
1. Research Institute of Exploration and Development,East China Branch of SINOPEC,Nanjing 210005,China
2. Sichuan Baohua Xinsheng Oil & Gas Operation Service Co. Ltd.,Chengdu 610000,China
全文: PDF(7359 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 

含气量是评价页岩气能否富集高产的主要参数之一,含气量越高越有利于页岩气井获得高产。传统含气量地震预测方法基于单属性、多属性的线性拟合或简单的神经网络,精度较低。基于深度神经网络的含气量预测方法,通过优选地震属性及最优化求解方法,选择合适的隐藏层个数、神经元个数、迭代次数来建立预测模型,从而预测页岩含气量,该方法能有效提高页岩含气量预测精度,为页岩气研究区地质评价、页岩气水平井井位布署提供支撑。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
张勇
马晓东
李彦婧
蔡景顺
关键词 深度学习页岩气含气量地震预测非线性    
Abstract

Gas content is one of the main parameters to evaluate whether shale gas can be enriched to obtain high-yield.The higher the gas content,the more favorable for shale gas wells to obtain high-yield.Traditional gas content seismic prediction methods are based on single-attribute,multi-attribute linear fitting or simple neural networks,and have low accuracy.The gas content prediction method is based on deep neural network.Through optimizing seismic attributes,optimizing the solution method and choosing the appropriate number of hidden layers,the number of neurons,and the number of iterations,a prediction model can be established to predict the gas content of shale,thus effectively improving the prediction accuracy of shale gas content and providing support for the geological evaluation of shale gas research areas and the deployment of shale gas horizontal wells.

Key wordsdeep learning    shale gas    shale gas content    seismic prediction    non-linear
收稿日期: 2020-11-03      出版日期: 2021-07-27
:  P631.4  
基金资助:国家科技重大专项(2016ZX05061);中国石油化工股份有限公司科技部项目(P19017-3)
作者简介: 张勇 (1986-),男,副研究员,2010年毕业于西南石油大学,主要从事地震资料解释及储层预测工作。Email: 253430528@qq.com
引用本文:   
张勇, 马晓东, 李彦婧, 蔡景顺. 深度学习在南川页岩气含气量预测中的应用[J]. 物探与化探, 2021, 45(3): 569-575.
ZHANG Yong, MA Xiao-Dong, LI Yan-Jing, CAI Jing-Shun. The application of deep learning to the shale gas content prediction in Nanchuan(South Sichuan). Geophysical and Geochemical Exploration, 2021, 45(3): 569-575.
链接本文:  
https://www.wutanyuhuatan.com/CN/10.11720/wtyht.2021.1507      或      https://www.wutanyuhuatan.com/CN/Y2021/V45/I3/569
Fig.1  深度神经网络结构
Fig.2  南川地区构造特征
Fig.3  A井五峰组—龙马溪组一段综合柱状图
Fig.4  属性个数优选
Fig.5  实测曲线与预测曲线叠合图
Fig.6  不同类型预测方法含气量预测剖面
Fig.7  优质页岩段平均含气量与构造叠合
[1] 赵金洲, 沈骋, 任岚, 等. 页岩储层不同赋存状态气体含气量定量预测——以四川盆地焦石坝页岩气田为例[J]. 天然气工业, 2017, 37(4):27-33.
[1] Zhao J Z, Shen C, Ren L, et al. Quantitative prediction of gas contents in different occurrence states of shale reservoirs:A case study of the Jiaoshiba shale gasfield in the Sichuan Basin[J]. Natural Gas Industry, 2017, 37(4):27-33.
[2] 郭旭升, 尹正武, 李金磊. 海相页岩含气量地震定量预测技术及其应用——以四川盆地焦石坝地区为例[J]. 石油地球物理勘探, 2015, 50(1):144-149.
[2] Guo X S, Yin Z W, Li J L. Quantitative seismic prediction of marine shale gas content,a case study in Jiaoshiba area,Sichuan basin[J]. Oil Geophysical Prospecting, 2015, 50(1):144-149.
[3] 陈超, 屈大鹏, 王明飞, 等. 川东南焦石坝地区海相泥页岩含气量预测方法探讨[J]. 石油物探, 2016, 55(4):597-605.
[3] Chen C, Qu D P, Wang M F, et al. Prediction method of gas content in marine mud shale at JSB area in southeast Sichuan Basin[J]. Geophysical Prospecting for Petroleum, 2016, 55(4):597-605.
[4] 马波, 黄天俊, 邹定永, 等. 海相页岩含气量地震定量预测方法研究——以川南长宁地区为例[J]. 天然气勘探与开发, 2018, 41(1):23-29.
[4] Ma B, Huang T J, Zou D Y, et al. A seismic-based quantitative method to predict gas content of marine shales: Examples from Changning area,southern Sichuan Basin[J]. Natural Gas Exploration and Development, 2018, 41(1):23-29.
[5] 张晓明, 石万忠, 舒志国, 等. 涪陵地区页岩含气量计算模型及应用[J]. 地球科学, 2017, 42(7):1157-1168.
[5] Zhang X M, Shi W Z, Shu Z G, et al. Calculation model of shale gas content and its application in Fuling area.[J]. Earth Science, 2017, 42(7):1157-1168.
[6] 王昊, 严加永, 付光明, 等. 深度学习在地球物理中的应用现状与前景[J]. 地球物理学进展, 2020, 35(2):642-655.
[6] Wang H, Yan J Y, Fu G M, et al. Current status and application prospect of deep learning in geophysics[J]. Progress in Geophysics, 2020, 35(2):642-655.
[7] 杨午阳, 魏新建, 何欣. 应用地球物理+AI的智能化物探技术发展策略[J]. 石油科技论坛, 2019, 38(5):40-47.
[7] Yang W Y, Wei X J, He X. Development plan for intelligent geophysical prospecting technology of applied geophysical+AI[J]. Oil Forum, 2019, 38(5):40-47.
[8] 吕尧, 单小彩, 霍守东, 等. 基于深度卷积神经网络的地震数据局部信噪比估计[J]. 地球物理学报, 2020, 63(1):320-328.
[8] Lyu Y, Shan X C, Huo S D, et al. Local SNR estimation of seismic data based on deep convolutional neural network[J]. Chinese Journal of Geophysics, 2020, 63(1):320-328.
[9] 张勇, 何贵松, 李彦婧, 等. 基于叠前反演的神经网络孔隙度预测技术——以南川地区为例[J]. 科学技术与工程, 2019, 19(25):83-89.
[9] Zhang Y, He G S, Li Y J, et al. Neural network porosity prediction technology based on prestack inversion:Take Nanchuan area as an example[J]. Science Technology and Engineering, 2019, 19(25):83-89.
[10] 郭彤楼, 蒋恕, 张培先, 等. 四川盆地外围常压页岩气勘探开发进展与攻关方向[J]. 石油实验地质, 2020, 42(5):837-845.
[10] Guo T L, Jiang S, Zhang P X, et al. Progress and direction of exploration and development of normally-pressured shale gas from the periphery of Sichuan Basin[J]. Petroleum Geology & Experiment, 2020, 42(5):837-845.
[11] 方志雄. 中国南方常压页岩气勘探开发面临的挑战及对策[J]. 油气藏评价与开发, 2019, 9(5):1-13.
[11] Fang Z X. Challenges and countermeasures for exploration and development of normal pressure shale gas in southern China[J]. Reservoir Evaluation and Development, 2019, 9(5):1-13.
[12] 何贵松, 何希鹏, 高玉巧, 等. 渝东南盆缘转换带金佛斜坡常压页岩气富集模式[J]. 天然气工业, 2020, 40(6):50-60.
[12] He G S, He X P, Gao Y Q, et al. Enrichment model of normal-pressure shale gas in the Jinfo slope of the basin-margin transition zone in Southeast Chongqing[J]. Natural Gas Industry, 2020, 40(6):50-60.
[13] 何希鹏, 王运海, 王彦祺, 等. 渝东南盆缘转换带常压页岩气勘探实践[J]. 中国石油勘探, 2020, 25(1):126-136.
[13] He X P, Wang Y H, Wang Y Q, et al. Exploration practices of normal-pressure shale gas in the marginal transition zone of the southeast Sichuan Basin[J]. China Petroleum Exploration, 2020, 25(1):126-136.
[14] 何希鹏, 何贵松, 高玉巧, 等. 渝东南盆缘转换带常压页岩气地质特征及富集高产规律[J]. 天然气工业, 2018, 38(12):1-14.
[14] He X P, He G S, Gao Y Q, et al. Geological characteristics and enrichment laws of normal-pressure shale gas in the basin-margin transition zone of SE Chongqing[J]. Natural Gas Industry, 2018, 38(12):1-14.
[15] 张玉玺, 刘洋, 张浩然, 等. 基于深度学习的多属性盐丘自动识别方法[J]. 石油地球物理勘探, 2020, 55(3):475-483.
[15] Zhang Y X, Liu Y, Zhang H R, et al. Multi-attribute automatic interpretation of salt domes based on deep learning[J]. Oil Geophysical Prospecting, 2020, 55(3):475-483.
[16] 丁燕, 杜启振, Qamar Yasin, 等. 基于深度学习的裂缝预测在S区潜山碳酸盐岩储层中的应用[J]. 石油物探, 2020, 59(2):267-275.
[16] Ding Y, Du Q Z, Qamar Y, et al. Fracture prediction based on deep learning:Application to a buried hill carbonate reservoir in the S area[J]. Geophysical Prospecting for Petroleum, 2020, 59(2):267-275.
[17] 王亚, 易远元, 王成泉, 等. 叠后反演技术在杨税务潜山裂缝孔隙型储层预测中的应用[J]. 物探与化探, 2020, 44(5):1208-1214.
[17] Wang Y, Yi Y Y, Wang C Q, et al. The application of post-stack inversion technology to the prediction of fracture and pore reservoir in Yangshuiwu buried hill[J]. Geophysical and Geochemical Exploration, 2020, 44(5):1208-1214.
[18] 陈志刚, 马文杰, 赵宏忠, 等. 利用曲率类属性预测储层裂缝的流程及应用实例[J]. 物探与化探, 2020, 44(5):1201-1207.
[18] Chen Z G, Ma W J, Zhao H Z, et al. A technical workflow of fracture prediction with curvature-related attributes and it applications[J]. Geophysical and Geochemical Exploration, 2020, 44(5):1201-1207.
[19] 王逸宸, 柳林涛, 许厚泽. 基于卷积神经网络识别重力异常体[J]. 物探与化探, 2020, 44(2):394-400.
[19] Wang Y C, Liu L T, Xu H Z. The identification of gravity anomaly body based on the convolutional neural network[J]. Geophysical and Geochemical Exploration, 2020, 44(2):394-400.
[20] 张昊, 朱培民, 顾元, 等. 基于深度学习的地震速度谱自动拾取方法[J]. 石油物探, 2019, 58(5):724-733.
[20] Zhang H, Zhu P M, Gu Y, et al. Velocity auto-picking from seismic velocity spectra based on deep learning[J]. Geophysical Prospecting for Petroleum, 2019, 58(5):724-733.
[1] 崔瑞康, 孙建孟, 刘行军, 文晓峰. 低阻页岩电阻率主控因素研究[J]. 物探与化探, 2022, 46(1): 150-159.
[2] 刘海宁, 韩宏伟, 魏文, 张云银, 赵景蒲. 高密度三维区沙四段灰岩有利储层地震预测[J]. 物探与化探, 2021, 45(5): 1281-1287.
[3] 欧居刚, 王小兰, 杨晓, 邓小江, 黄诚, 李文佳. 水平井地震导向技术探索与应用——以四川盆地复杂地区页岩气井为例[J]. 物探与化探, 2021, 45(3): 551-559.
[4] 刘昊娟. 地应力地震预测及其在南川页岩气开发中的应用[J]. 物探与化探, 2021, 45(3): 560-568.
[5] 吴国培, 张莹莹, 张博文, 赵华亮. 基于深度学习的中心回线瞬变电磁全区视电阻率计算[J]. 物探与化探, 2021, 45(3): 750-757.
[6] 刘伟男, 张超谟, 朱林奇, 胡松, 孔政, 邓瑞. 页岩气水平井TOC测井评价新方法[J]. 物探与化探, 2021, 45(2): 423-431.
[7] 赵广学, 阮帅, 吴肃元. 隧道勘探AMT数据二维非线性共轭梯度反演的关键参数探讨[J]. 物探与化探, 2021, 45(2): 480-489.
[8] 梁立锋, 刘秀娟, 张宏兵, 陈程浩, 陈锦华. 超参数对GRU-CNN混合深度学习弹性阻抗反演影响研究[J]. 物探与化探, 2021, 45(1): 133-139.
[9] 臧子婧, 吴海波, 丁海, 张平松, 董守华. 基于优选地震属性与PSO-BP模型的煤层含气量预测[J]. 物探与化探, 2020, 44(6): 1381-1386.
[10] 李帝铨, 汪振兴, 胡艳芳, 王涵, 苏煜堤. 广域电磁法在武陵山区页岩气勘探中的探索应用——以黔北桐梓地区为例[J]. 物探与化探, 2020, 44(5): 991-998.
[11] 赵文举, 赵荔, 杨战军, 陶德强. 插值切割位场分离方法改进及其在资料处理中的应用[J]. 物探与化探, 2020, 44(4): 886-893.
[12] 王逸宸, 柳林涛, 许厚泽. 基于卷积神经网络识别重力异常体[J]. 物探与化探, 2020, 44(2): 394-400.
[13] 田巍, 李旭兵, 王保忠. 大地电磁测深在湘东南坳陷页岩气勘探中的应用[J]. 物探与化探, 2019, 43(2): 281-289.
[14] 许智博, 谭捍东. ZTEM二维非线性共轭梯度反演研究[J]. 物探与化探, 2019, 43(2): 393-400.
[15] 梁亚林, 原文涛. 测井预测煤层气含量及分布规律——以山西省沁水煤田为例[J]. 物探与化探, 2018, 42(6): 1144-1149.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-3
版权所有 © 2021《物探与化探》编辑部
通讯地址:北京市学院路29号航遥中心 邮编:100083
电话:010-62060192;62060193 E-mail:whtbjb@sina.com