Article(id=1327707271020262081, tenantId=1146029695717560320, journalId=1327236479169368089, issueId=1327706995160887574, articleNumber=null, orderNo=null, doi=10.11720/wtyht.2026.1344, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1759075200000, receivedDateStr=2025-09-29, revisedDate=1768924800000, revisedDateStr=2026-01-21, acceptedDate=1769961600000, acceptedDateStr=2026-02-02, onlineDate=1794479681018, onlineDateStr=2026-11-12, pubDate=1775750400000, pubDateStr=2026-04-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794479681018, onlineIssueDateStr=2026-11-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794479681018, creator=13701087609, updateTime=1794479681018, updator=13701087609, issue=Issue{id=1327706995160887574, tenantId=1146029695717560320, journalId=1327236479169368089, year='2026', volume='50', issue='2', pageStart='189', pageEnd='408', issueExtLink='null', onlineDate='null', pubDate='1775750400000', pubDateStr='2026-04-10', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794479615249, creator='13701087609', updateTime=1794532649517, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327929437636636816, tenantId=1146029695717560320, journalId=1327236479169368089, issueId=1327706995160887574, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327929437636636817, tenantId=1146029695717560320, journalId=1327236479169368089, issueId=1327706995160887574, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=319, endPage=329, ext={EN=ArticleExt(id=1327707271175451330, articleId=1327707271020262081, tenantId=1146029695717560320, journalId=1327236479169368089, language=EN, title=A CNN-BiLSTM model-based porosity prediction method for tight sandstone reservoirs, columnId=null, journalTitle=Geophysical and Geochemical Exploration, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Porosity is a critical parameter for characterizing reservoir physical properties. The accuracy of porosity prediction holds significant implications for hydrocarbon exploration and production, as well as the geological modeling and fine-scale evaluation of hydrocarbon reservoirs. Considering the characteristics of tight sandstone reservoirs, such as low porosity, low permeability, and strong heterogeneity, this study proposed a reservoir porosity prediction model that integrates the convolutional neural network (CNN) and bidirectional long short-term memory(BiLSTM). The CNN-BiLSTM model is used to extract features from log data and establish complex nonlinear correlations between these features and porosity parameters. First, using petrophysical models, sensitive elastic parameters, which are significantly correlated with porosity, are selected as input parameters. Second, the spatially dependent features are extracted from the inversion data using the CNN. Third, the temporal dependencies throughout the data sequence are captured by BiLSTM. These processes contribute to effective porosity prediction. The test results of three wells in oilfield A, Kaiping sag, demonstrate that compared to conventional deep learning methods, the CNN-BiLSTM model achieved higher accuracy and lateral resolution in porosity prediction, verifying its effectiveness. Furthermore, the CNN-BiLSTM model was applied for the 3D reservoir porosity prediction by calculating the porosity data volume from elastic parameter volumes obtained through reservoir inversion. Overall, this study provides a novel approach for predicting reservoir porosity in the sparse well area of oilfield A, offshore Kaiping sag.

, authors=Li LI, Zheng DONG, Kai HOU, Cheng WU, Ji-Jun PENG, authorsList=Li LI, Zheng DONG, Kai HOU, Cheng WU, Ji-Jun PENG, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Geophysical and Geochemical Exploration. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1327707274719638235, articleId=1327707271020262081, tenantId=1146029695717560320, journalId=1327236479169368089, language=CN, title=基于CNN-BiLSTM模型的致密砂岩储层孔隙度预测方法, columnId=1327707063590957858, journalTitle=物探与化探, columnName=方法研究·信息处理·仪器研制, runingTitle=null, highlight=null, articleAbstract=

孔隙度是描述储层物理性质的重要参数,孔隙度预测的准确性对油气勘探开发、油气藏地质建模和精细评价具有重要意义。针对致密砂岩储层低孔、低渗及非均质性强的特点,本文提出一种融合卷积神经网络(convolutional neural network,CNN)和双向长短期记忆网络(bidirectional long short-term memory, BiLSTM)的储层孔隙度预测模型,用于从测井数据中提取特征并建立其与孔隙度参数之间的复杂非线性关联。首先,依据岩石物理模型筛选出与孔隙度显著相关的敏感弹性参数作为输入参数,随后借助卷积神经网络提取反演数据中的空间依赖特征,进一步通过双向长短时记忆神经网络捕捉其前后的时序依赖关系,最终实现孔隙度的有效预测。开平凹陷A油田3口井的测试结果表明,相比常规深度学习方法,CNN-BiLSTM模型的孔隙度预测结果具有更好的精度及横向分辨率,验证了该模型的有效性。在此基础上,利用该模型开展三维储层孔隙度预测,通过输入储层反演获得的弹性参数数据体计算出孔隙度数据体,为海上开平凹陷A油田少井区储层孔隙度预测提供了新的研究思路。

, authors=李黎, 董政, 侯凯, 吴成, 彭己君, authorsList=李黎, 董政, 侯凯, 吴成, 彭己君, authorCompany=null, correspAuthors=null, authorNote=

李黎(1981−),女,硕士研究生学历,高级工程师,主要从事油藏地球物理研究工作。Email:

, correspAuthorsNote=null, copyrightStatement=版权所有 © 2026 物探与化探编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=DSfK1qXiNk5/ojKNmK5lPg==, magXml=UwQJy/iWyL+j3ELcG2Ptog==, pdfUrl=null, pdf=mJn0VvKDeGVQve+U/LN2Ug==, pdfFileSize=5083444, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=UPTjvfq2tbXdyDKG85Zg0Q==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=X2J6iyItMO44HySQ/JQbXw==, mapNumber=null, fund=null)}, authors=[Author(id=1327707274996462304, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lili12@cnooc.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275097125602, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707274996462304, language=EN, stringName=Li LI, firstName=Li, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707275197788899, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707274996462304, language=CN, stringName=李黎, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio={"content":"

李黎(1981−),女,硕士研究生学历,高级工程师,主要从事油藏地球物理研究工作。Email:

"}, bioImg=null, bioContent=

李黎(1981−),女,硕士研究生学历,高级工程师,主要从事油藏地球物理研究工作。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707275264897765, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275344589543, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275264897765, language=EN, stringName=Zheng DONG, firstName=Zheng, middleName=null, lastName=DONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707275420087016, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275264897765, language=CN, stringName=董政, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707275495584490, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275604636396, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275495584490, language=EN, stringName=Kai HOU, firstName=Kai, middleName=null, lastName=HOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707275675939565, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275495584490, language=CN, stringName=侯凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707275747242735, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275835323121, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275747242735, language=EN, stringName=Cheng WU, firstName=Cheng, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707277513044722, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275747242735, language=CN, stringName=吴成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707277592736500, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707277697594102, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707277592736500, language=EN, stringName=Ji-Jun PENG, firstName=Ji-Jun, middleName=null, lastName=PENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707277802451703, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707277592736500, language=CN, stringName=彭己君, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])])], keywords=[Keyword(id=1327707277911503608, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, orderNo=1, keyword=Kaiping sag), Keyword(id=1327707278012166905, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, orderNo=2, keyword=CNN-BiLSTM model), Keyword(id=1327707278087664378, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, orderNo=3, keyword=deep learning), Keyword(id=1327707278171550459, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, orderNo=4, keyword=porosity prediction), Keyword(id=1327707278238659324, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, orderNo=5, keyword=tight sandstone), Keyword(id=1327707278309962493, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, orderNo=1, keyword=开平凹陷), Keyword(id=1327707278385459966, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, orderNo=2, keyword=CNN-BiLSTM模型), Keyword(id=1327707278460957439, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, orderNo=3, keyword=深度学习), Keyword(id=1327707278528066304, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, orderNo=4, keyword=孔隙度预测), Keyword(id=1327707278586786561, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, orderNo=5, keyword=致密砂岩)], refs=[Reference(id=1327707282449740575, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=杨柳青, 查蓓, 陈伟. 基于深度神经网络的砂岩储层孔隙度预测方法[J]. 中国科技论文, 2020, 15(1): 73−80., articleTitle=null, refAbstract=null), Reference(id=1327707282516849440, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang L Q, Zha B, Chen W. Prediction method of reservoir porosity based on deep neural network[J]. China Sciencepaper, 2020, 15(1): 73−80., articleTitle=null, refAbstract=null), Reference(id=1327707282592346913, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=汪锐, 李芳, 刘仕友, 等. 岩石物理建模引导的低渗储层参数预测方法[J]. 煤田地质与勘探, 2024, 52(8): 187−197., articleTitle=null, refAbstract=null), Reference(id=1327707282655261474, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang R, Li F, Liu S Y, et al. A petrophysical modeling-guided method for predicting parameters of low-permeability reservoirs[J]. Coal Geology & Exploration, 2024, 52(8): 187−197., articleTitle=null, refAbstract=null), Reference(id=1327707282726564643, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Saito H, Kato M. Machine learning technique to find quantum many-body ground states of bosons on a lattice[J]. Journal of the Physical Society of Japan, 2018, 87(1): 014001., articleTitle=null, refAbstract=null), Reference(id=1327707282797867812, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Mahdy A, Zakaria W, Helmi A, et al. Machine learning approach for core permeability prediction from well logs in Sandstone Reservoir, Mediterranean Sea, Egypt[J]. Journal of Applied Geophysics, 2024, 220: 105249., articleTitle=null, refAbstract=null), Reference(id=1327707282860782373, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=陈蓉, 王峰. 基于MATLAB的BP神经网络在储层物性预测中的应用[J]. 测井技术, 2009, 33(1): 75−78., articleTitle=null, refAbstract=null), Reference(id=1327707282919502630, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen R, Wang F. Application of MATLAB-based of BP neural network in reservoir parameters prediction[J]. Well Logging Technology, 2009, 33(1): 75−78., articleTitle=null, refAbstract=null), Reference(id=1327707282982417191, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=严禛, 伍星蓉. 基于BFO-BP神经网络的储层预测研究[J]. 能源与环保, 2017, 39(7): 210−213., articleTitle=null, refAbstract=null), Reference(id=1327707283041137448, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Z, Wu X R. Study on BFO-BP neural network to reservoir thickness prediction[J]. China Energy and Environmental Protection, 2017, 39(7): 210−213., articleTitle=null, refAbstract=null), Reference(id=1327707283095663401, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=郑宇哲, 叶朝辉, 刘西恩, 等. 基于深度学习的储层物性参数预测方法研究[J]. 电子世界, 2018(4): 23−26., articleTitle=null, refAbstract=null), Reference(id=1327707283154383658, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng Y Z, Ye Z H, Liu X E, et al. Research on prediction method of reservoir physical properties based on deep learning[J]. Electronics World, 2018(4): 23−26., articleTitle=null, refAbstract=null), Reference(id=1327707283221492523, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=朱林奇, 张冲, 周雪晴, 等. 融合深度置信网络与与核极限学习机算法的核磁共振测井储层渗透率预测方法[J]. 计算机应用, 2017, 37(10): 3034−3038., articleTitle=null, refAbstract=null), Reference(id=1327707283276018476, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu L Q, Zhang C, Zhou X Q, et al. Nuclear magnetic resonance logging reservoir permeability prediction method based on deep belief network and kernel extreme learning machine algorithm[J]. Journal of Computer Applications, 2017, 37(10): 3034−3038., articleTitle=null, refAbstract=null), Reference(id=1327707283334738733, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=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., articleTitle=null, refAbstract=null), Reference(id=1327707283389264686, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Duan Y X, Li G T, Sun Q F. Application of convolutional neural network in reservoir prediction[J]. Journal on Communications, 2016, 37(S1): 1−9., articleTitle=null, refAbstract=null), Reference(id=1327707283452179247, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=付超, 林年添, 张栋, 等. 多波地震深度学习的油气储层分布预测案例[J]. 地球物理学报, 2018, 61(1): 293−303., articleTitle=null, refAbstract=null), Reference(id=1327707283515093808, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Fu C, Lin N T, Zhang D, et al. Prediction of reservoirs using multi-component seismic data and the deep learning method[J]. Chinese Journal of Geophysics, 2018, 61(1): 293−303., articleTitle=null, refAbstract=null), Reference(id=1327707283586396977, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Hamidi H, Rafati R. Prediction of oil reservoir porosity based on BP-ANN[C]//Malacca:2012 International Conference on Innovation Management and Technology Research, IEEE, 2012: 241-246., articleTitle=null, refAbstract=null), Reference(id=1327707283674477362, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=王冉. 基于深度学习的储层参数预测系统研究[D]. 大庆: 东北石油大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1327707283741586227, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang R. Research on reservoir parameter prediction system based on deep learning[D]. Daqing: Northeast Petroleum University, 2023., articleTitle=null, refAbstract=null), Reference(id=1327707283800306484, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang J, Cao J X, Yuan S. Deep learning reservoir porosity prediction method based on a spatiotemporal convolution bi-directional long short-term memory neural network model[J]. Geomechanics for Energy and the Environment, 2022, 32: 100282., articleTitle=null, refAbstract=null), Reference(id=1327707283859026741, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=邵蓉波, 肖立志, 廖广志, 等. 基于多任务学习的测井储层参数预测方法[J]. 地球物理学报, 2022, 65(5): 1883−1895., articleTitle=null, refAbstract=null), Reference(id=1327707283934524214, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Shao R B, Xiao L Z, Liao G Z, et al. Multitask learning based reservoir parameters prediction with geophysical logs[J]. Chinese Journal of Geophysics, 2022, 65(5): 1883−1895., articleTitle=null, refAbstract=null), Reference(id=1327707283997438775, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=赵军, 张涛, 何胜林, 等. 基于参数优选的储层渗透率深度置信网络模型预测初探[J]. 油气藏评价与开发, 2021, 11(4): 577−585., articleTitle=null, refAbstract=null), Reference(id=1327707284064547640, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao J, Zhang T, He S L, et al. Prediction of reservoir permeability by deep belief network based on optimized parameters[J]. Petroleum Reservoir Evaluation and Development, 2021, 11(4): 577−585., articleTitle=null, refAbstract=null), Reference(id=1327707284127462201, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=王俊, 曹俊兴, 周欣. 基于深度双向循环神经网络的储层孔隙度预测[J]. 地球物理学进展, 2022, 37(1): 267−274., articleTitle=null, refAbstract=null), Reference(id=1327707284186182458, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang J, Cao J X, Zhou X. Reservoir porosity prediction based on deep bidirectional recurrent neural network[J]. Progress in Geophysics, 2022, 37(1): 267−274., articleTitle=null, refAbstract=null), Reference(id=1327707284265874235, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=王丽君. 基于深度学习的储层孔隙度预测研究[D]. 青岛: 青岛理工大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1327707284332983100, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang L J. Research on reservoir porosity prediction based on deep learning[D]. Qingdao: Qingdao University of Technology, 2023., articleTitle=null, refAbstract=null), Reference(id=1327707284400091965, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=徐颖晋. 基于CNN-Transformer的致密砂岩储层参数预测研究[D]. 抚州: 东华理工大学, 2024., articleTitle=null, refAbstract=null), Reference(id=1327707284458812222, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Y J. Research on tight sandstone reservoir parameter prediction based on CNN-Transformer[D]. Fuzhou: East China Institute of Technology, 2024., articleTitle=null, refAbstract=null), Reference(id=1327707284517532479, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=孙婉峰. 基于Transformer的储层参数预测算法研究与应用[D]. 西安: 西安石油大学, 2025., articleTitle=null, refAbstract=null), Reference(id=1327707284584641344, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun W F. Research and application of reservoir parameter prediction algorithm based on Transformer[D]. Xi’an: Xi’an Shiyou University, 2025., articleTitle=null, refAbstract=null), Reference(id=1327707284655944513, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=高阳东, 彭光荣, 陈兆明, 等. 珠江口盆地开平凹陷深水古近系勘探重大发现及意义[J]. 石油学报, 2023, 44(7): 1029−1040., articleTitle=null, refAbstract=null), Reference(id=1327707284727247682, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Y D, Peng G R, Chen Z M, et al. Breakthrough and significance of deep-water Paleogene exploration in Kaiping Sag, Pearl River Mouth Basin[J]. Acta Petrolei Sinica, 2023, 44(7): 1029−1040., articleTitle=null, refAbstract=null), Reference(id=1327707286383997763, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=刘怡伟. 基于深度神经网络的几类时间序列预测模型研究[D]. 大连: 大连海事大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1327707286459495236, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Y W. A research on several types of time series forecast models based on deep neural network[D]. Dalian: Dalian Maritime University, 2020., articleTitle=null, refAbstract=null), Reference(id=1327707286597907269, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=古瑶, 解海军, 周子鹏, 等. 基于Attention机制的CNN-BiLSTM瞬变电磁实时反演方法[J]. 煤田地质与勘探, 2023, 51(10): 134−143., articleTitle=null, refAbstract=null), Reference(id=1327707286665016134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Gu Y, Xie H J, Zhou Z P, et al. An Attention mechanism-based CNN-BiLSTM real-time transient electromagnetic method[J]. Coal Geology & Exploration, 2023, 51(10): 134−143., articleTitle=null, refAbstract=null), Reference(id=1327707286748902215, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=李青, 张新燕, 马天娇, 等. 基于SSA-CNN-BiGRU-Attention的超短期风电功率预测模型[J]. 电机与控制应用, 2023, 50(5): 61−71., articleTitle=null, refAbstract=null), Reference(id=1327707286820205384, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Q, Zhang X Y, Ma T J, et al. Ultra-short term forecasting model of wind power based on SSA-CNN-BiGRU-attention[J]. Electric Machines & Control Application, 2023, 50(5): 61−71., articleTitle=null, refAbstract=null), Reference(id=1327707286895702857, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Hochreiter S, Schmidhuber J. Long short-term memory[J].Neural Comput.,1997, 9 (8): 1735-1780., articleTitle=null, refAbstract=null), Reference(id=1327707286962811722, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=梁宏涛, 刘硕, 杜军威, 等. 深度学习应用于时序预测研究综述[J]. 计算机科学与探索, 2023, 17(6): 1285−1300., articleTitle=null, refAbstract=null), Reference(id=1327707287025726283, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang H T, Liu S, Du J W, et al. Review of deep learning applied to time series prediction[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(6): 1285−1300., articleTitle=null, refAbstract=null), Reference(id=1327707287088640844, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=刘俊, 曹俊兴, 丁蔚楠, 等. 基于双向长短期记忆神经网络的储层孔隙度预测方法研究[J]. 地球物理学进展, 2022, 37(5): 1993−2000., articleTitle=null, refAbstract=null), Reference(id=1327707287151555405, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu J, Cao J X, Ding W N, et al. Research on reservoir porosity prediction method based on bidirectional longshort-term memory neural network[J]. Progress in Geophysics, 2022, 37(5): 1993−2000., articleTitle=null, refAbstract=null), Reference(id=1327707287214469966, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang N, Li G, Zhao P, et al. Porosity prediction from pre-stack seismic data via a data-driven approach[J]. Journal of Applied Geophysics, 2023, 211: 104947., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])], figs=[ArticleFig(id=1327707278695838466, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 1, caption=Geographical location of Kaiping Sag in the Pearl river mouth basin, figureFileSmall=uGA1Np+s7/+HE+87JNoC2A==, figureFileBig=UPTjvfq2tbXdyDKG85Zg0Q==, tableContent=null), ArticleFig(id=1327707278758753027, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图1, caption=珠江口盆地开平凹陷地理位置, figureFileSmall=uGA1Np+s7/+HE+87JNoC2A==, figureFileBig=UPTjvfq2tbXdyDKG85Zg0Q==, tableContent=null), ArticleFig(id=1327707278926525188, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 2, caption=Physical property characteristics of the Enping Formation in Kaiping A oilfield, figureFileSmall=L3yWscOh60VqOkAS5qPTZg==, figureFileBig=TpYaBirvbwvYcR+QUocpdg==, tableContent=null), ArticleFig(id=1327707278985245445, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图2, caption=开平A油田恩平组物性特征, figureFileSmall=L3yWscOh60VqOkAS5qPTZg==, figureFileBig=TpYaBirvbwvYcR+QUocpdg==, tableContent=null), ArticleFig(id=1327707279039771398, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 3, caption=Forward simulation curve of elastic parameters with variable porosity, figureFileSmall=Xaeen5PgotrBAZewFjuKQQ==, figureFileBig=30BTGXaCZ6fndXAN/uyJbw==, tableContent=null), ArticleFig(id=1327707279102685959, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图3, caption=变孔隙度的弹性参数正演模拟曲线, figureFileSmall=Xaeen5PgotrBAZewFjuKQQ==, figureFileBig=30BTGXaCZ6fndXAN/uyJbw==, tableContent=null), ArticleFig(id=1327707279165600520, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 4, caption=Relative variation of elastic parameters, figureFileSmall=Lktx1i7/C1rIWVfzHxx/Tg==, figureFileBig=jW8o+iMKLe60p1rtOGh9tg==, tableContent=null), ArticleFig(id=1327707279249486601, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图4, caption=弹性参数的相对变化量, figureFileSmall=Lktx1i7/C1rIWVfzHxx/Tg==, figureFileBig=jW8o+iMKLe60p1rtOGh9tg==, tableContent=null), ArticleFig(id=1327707279341761290, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 5, caption=Schematic of CNN structure, figureFileSmall=k/IMHXkCJqJD3pEClK9I+Q==, figureFileBig=MelqZt7IKUZjmhwanwbTaA==, tableContent=null), ArticleFig(id=1327707279408870155, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图5, caption=CNN结构示意, figureFileSmall=k/IMHXkCJqJD3pEClK9I+Q==, figureFileBig=MelqZt7IKUZjmhwanwbTaA==, tableContent=null), ArticleFig(id=1327707279488561932, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 6, caption=Schematic of LSTM network structure, figureFileSmall=/MvEp1UScXue+RREQTbT7w==, figureFileBig=bbEWiIuShtB5fejrtQMIZQ==, tableContent=null), ArticleFig(id=1327707279572448013, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图6, caption=LSTM网络结构示意, figureFileSmall=/MvEp1UScXue+RREQTbT7w==, figureFileBig=bbEWiIuShtB5fejrtQMIZQ==, tableContent=null), ArticleFig(id=1327707279635362574, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 7, caption=Schematic of BiLSTM network structure, figureFileSmall=3FYjArHZ8EY0eAhx2hsynQ==, figureFileBig=AP0Xbon5FfOEZ1t5V6CcIA==, tableContent=null), ArticleFig(id=1327707279685694223, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图7, caption=BiLSTM网络结构示意, figureFileSmall=3FYjArHZ8EY0eAhx2hsynQ==, figureFileBig=AP0Xbon5FfOEZ1t5V6CcIA==, tableContent=null), ArticleFig(id=1327707279748608784, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 8, caption=CNN-BiLSTM porosity prediction model, figureFileSmall=VGGnloxMsaAbwepMydlWUg==, figureFileBig=bAkS7Wf8ByrNrd27iXmO4w==, tableContent=null), ArticleFig(id=1327707279803134737, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图8, caption=CNN-BiLSTM孔隙度预测模型, figureFileSmall=VGGnloxMsaAbwepMydlWUg==, figureFileBig=bAkS7Wf8ByrNrd27iXmO4w==, tableContent=null), ArticleFig(id=1327707279891215122, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 9, caption=Comparison of prediction results of different models on KPA1 well, figureFileSmall=RlrpZd+m1u0x2ZGb1xzc2w==, figureFileBig=DW+JomhalbYsGpdrWEjX+g==, tableContent=null), ArticleFig(id=1327707279949935379, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图9, caption=KPA1井上不同模型预测结果对比, figureFileSmall=RlrpZd+m1u0x2ZGb1xzc2w==, figureFileBig=DW+JomhalbYsGpdrWEjX+g==, tableContent=null), ArticleFig(id=1327707280021238548, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 10, caption=Intersection plot of true and predicted values and error distribution histogram for different models, figureFileSmall=ZPSHyJgbG7OMHulwpIKB9w==, figureFileBig=/OZzIke2HaavesJ3iE6Ecw==, tableContent=null), ArticleFig(id=1327707280176427797, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图10, caption=不同模型的真实值与预测值交会以及误差分布直方图, figureFileSmall=ZPSHyJgbG7OMHulwpIKB9w==, figureFileBig=/OZzIke2HaavesJ3iE6Ecw==, tableContent=null), ArticleFig(id=1327707280243536662, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 11, caption=Profile of pre stack AVO elastic inversion results for the third segment of Enping Formation, figureFileSmall=Xg11Tjy1pbD3obLrrkpiPg==, figureFileBig=A4bkR7LqICx5o0wQRBnjWQ==, tableContent=null), ArticleFig(id=1327707281933841176, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图11, caption=恩三段叠前AVO弹性参数反演结果剖面, figureFileSmall=Xg11Tjy1pbD3obLrrkpiPg==, figureFileBig=A4bkR7LqICx5o0wQRBnjWQ==, tableContent=null), ArticleFig(id=1327707282013532953, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Figure 12, caption=Prediction profile(left) and plan(right) of porosity in the third segment of Enping Formation, figureFileSmall=EKoMmDb+aDyNuxCZyeKfTw==, figureFileBig=HTOwBVyrvFcZjipAhF0VAg==, tableContent=null), ArticleFig(id=1327707282072253210, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=图12, caption=恩三段孔隙度预测剖面(左)与平面(右), figureFileSmall=EKoMmDb+aDyNuxCZyeKfTw==, figureFileBig=HTOwBVyrvFcZjipAhF0VAg==, tableContent=null), ArticleFig(id=1327707282139362075, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Table 1, caption=

Statistics of logging data for KPA1 well at layer 321

, figureFileSmall=null, figureFileBig=null, tableContent=
参数countmeanstdmin25%50%75%max
AI/(m·s−1·g·cm−3)17061.08×1077.59×1057.20×1061.04×1071.07×1071.12×1071.42×107
EE/GPa17063.82×10105.59×1091.85×10103.49×10103.86×10104.14×10105.97×1010
KK/GPa17062.59×10103.67×1091.53×10102.35×10102.54×10102.80×10104.67×1010
LAMRHO/(GPa·g·cm−3)17063.95×10139.03×10121.78×10133.26×10133.89×10134.59×10138.18×1013
SI/(m·s−1·g·cm−3)17066.18×1065.01×1053.89×1065.88×1066.23×1066.48×1067.89×106
UU/GPa17061.53×10102.45×1097.11×1091.38×10101.55×10101.68×10102.40×1010
UURHO/(GPa·g·cm−3)17063.84×10136.10×10121.50×10133.4×10133.87×10134.19×10136.21×1013
VV17060.25230.030.140.220.250.270.32
VP/(m·s−1)17064278.85272.793291.574146.904317.284423.805482.01
Vp/Vs17061.740.071.551.681.741.801.95
Vs/(m·s−1)17062458.10211.901763.882330.272484.132609.583041.91
PIGE/(GPa·g·cm−3)17068.664.410.0014.369.6212.6117.52
), ArticleFig(id=1327707282214859548, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=表1, caption=

KPA1井在321层段的测井数据统计

, figureFileSmall=null, figureFileBig=null, tableContent=
参数countmeanstdmin25%50%75%max
AI/(m·s−1·g·cm−3)17061.08×1077.59×1057.20×1061.04×1071.07×1071.12×1071.42×107
EE/GPa17063.82×10105.59×1091.85×10103.49×10103.86×10104.14×10105.97×1010
KK/GPa17062.59×10103.67×1091.53×10102.35×10102.54×10102.80×10104.67×1010
LAMRHO/(GPa·g·cm−3)17063.95×10139.03×10121.78×10133.26×10133.89×10134.59×10138.18×1013
SI/(m·s−1·g·cm−3)17066.18×1065.01×1053.89×1065.88×1066.23×1066.48×1067.89×106
UU/GPa17061.53×10102.45×1097.11×1091.38×10101.55×10101.68×10102.40×1010
UURHO/(GPa·g·cm−3)17063.84×10136.10×10121.50×10133.4×10133.87×10134.19×10136.21×1013
VV17060.25230.030.140.220.250.270.32
VP/(m·s−1)17064278.85272.793291.574146.904317.284423.805482.01
Vp/Vs17061.740.071.551.681.741.801.95
Vs/(m·s−1)17062458.10211.901763.882330.272484.132609.583041.91
PIGE/(GPa·g·cm−3)17068.664.410.0014.369.6212.6117.52
), ArticleFig(id=1327707282290357021, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=EN, label=Table 2, caption=

Prediction errors and determination coefficients of different prediction models for KPA1 well

, figureFileSmall=null, figureFileBig=null, tableContent=
模型测试集
RMSE $ {R}^{2} $
CNN0.90490.8547
LSTM0.70590.9099
CNN-BiLSTM0.65460.9369
), ArticleFig(id=1327707282353271582, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, language=CN, label=表2, caption=

KPA1井不同预测模型的预测误差和决定系数

, figureFileSmall=null, figureFileBig=null, tableContent=
模型测试集
RMSE $ {R}^{2} $
CNN0.90490.8547
LSTM0.70590.9099
CNN-BiLSTM0.65460.9369
)], attaches=null, journal=Journal(id=1327236024032858132, delFlag=0, nameCn=物探与化探, nameEn=Geophysical and Geochemical Exploration, nameHistory1=null, nameHistory2=null, issn=1000-8918, eissn=null, cn=11-1906/P, coden=null, periodic=1, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=Q9arnnRH1j311w2tJP+SLw==, journalPrice=null, startedYear=null, abbrevIsoEn=Geophysical and Geochemical Exploration, journalRemark=null, publicationField=null, createdTime=1794367326984, updatedTime=1794367816166, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=W, firstLetterEn=W, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=Q9arnnRH1j311w2tJP+SLw==, picEn=83mUIs+38HfkGogm/M2tdQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1327238075878584575, language=CN, name=物探与化探, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1794367816180, updatedTime=1794367816180, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.wutanyuhuatan.com/journalx_wt/authorLogOn.action, submissionEditorUrl=https://www.wutanyuhuatan.com/journalx_wt/editorLogOn.action, submissionReviewUrl=https://www.wutanyuhuatan.com/journalx_wt/expertLogOn.action, submissionCeEditorUrl=https://www.wutanyuhuatan.com/journalx_wt/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1327238075937304832, language=EN, name=Geophysical and Geochemical Exploration, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1794367816194, updatedTime=1794367816194, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.wutanyuhuatan.com/journalx_wt/authorLogOn.action, submissionEditorUrl=https://www.wutanyuhuatan.com/journalx_wt/editorLogOn.action, submissionReviewUrl=https://www.wutanyuhuatan.com/journalx_wt/expertLogOn.action, submissionCeEditorUrl=https://www.wutanyuhuatan.com/journalx_wt/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1327236479169368089, websiteList=[Website(id=1327238745817985575, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1327236479169368089, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/wtyht/CN, language=CN, createTime=1794367975906, createBy=18614031015, updateTime=1794368283036, updateBy=18614031015, name=物探与化探-中文, tplId=1146099689490845704, title=物探与化探, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1327240131204984887, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=articleTextType, value=kx, createTime=1794368306208, updateTime=1794368306208, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131171430452, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=banner, value=null, createTime=1794368306200, updateTime=1794368306200, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131234345018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=grayFlag, value=0, createTime=1794368306215, updateTime=1794368306215, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131163041843, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=logo, value=https://castjournals.cast.org.cn/joweb/wtyht/CN/file/pic?fileId=vZZWCUTLvEhr0THTPpfgig==, createTime=1794368306198, updateTime=1794368306198, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131255316540, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=minRunFlag, value=0, createTime=1794368306220, updateTime=1794368306220, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131196596278, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/wtyht/CN/file/pic, createTime=1794368306206, updateTime=1794368306206, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131246927931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=silenceFlag, value=0, createTime=1794368306218, updateTime=1794368306218, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131184013365, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1794368306203, updateTime=1794368306203, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131213373496, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=themeColor, value=null, createTime=1794368306210, updateTime=1794368306210, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240131225956409, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745817985575, code=themeStyle, value=null, createTime=1794368306213, updateTime=1794368306213, creator=18614031015, updator=18614031015)]), Website(id=1327238745885094441, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1327236479169368089, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/wtyht/EN, language=EN, createTime=1794367975922, createBy=18614031015, updateTime=1794368278613, updateBy=18614031015, name=物探与化探-英文, tplId=1146101810881728533, title=Geophysical and Geochemical Exploration, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1327240160451866691, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=articleTextType, value=kx, createTime=1794368313181, updateTime=1794368313181, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160430895168, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=banner, value=null, createTime=1794368313177, updateTime=1794368313177, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160468643910, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=grayFlag, value=0, createTime=1794368313185, updateTime=1794368313185, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160422506559, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=logo, value=https://castjournals.cast.org.cn/joweb/wtyht/EN/file/pic?fileId=vZZWCUTLvEhr0THTPpfgig==, createTime=1794368313174, updateTime=1794368313174, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160481226824, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=minRunFlag, value=0, createTime=1794368313188, updateTime=1794368313188, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160443478082, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/wtyht/EN/file/pic, createTime=1794368313180, updateTime=1794368313180, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160477032519, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=silenceFlag, value=0, createTime=1794368313187, updateTime=1794368313187, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160439283777, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1794368313178, updateTime=1794368313178, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160456060996, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=themeColor, value=null, createTime=1794368313182, updateTime=1794368313182, creator=18614031015, updator=18614031015), WebsiteProps(id=1327240160464449605, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1327238745885094441, code=themeStyle, value=null, createTime=1794368313184, updateTime=1794368313184, creator=18614031015, updator=18614031015)])], journalTitle=物探与化探, weixinUrl=null, journalUrl=https://www.wutanyuhuatan.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Geophysical and Geochemical Exploration, journalPhotoCn=Q9arnnRH1j311w2tJP+SLw==, journalPhotoEn=83mUIs+38HfkGogm/M2tdQ==, journalFirstLetter=W, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/wtyht/CN/10.11720/wtyht.2026.1344, detailUrlEn=https://castjournals.cast.org.cn/joweb/wtyht/EN/10.11720/wtyht.2026.1344, pdfUrlCn=https://castjournals.cast.org.cn/joweb/wtyht/CN/PDF/10.11720/wtyht.2026.1344, pdfUrlEn=https://castjournals.cast.org.cn/joweb/wtyht/EN/PDF/10.11720/wtyht.2026.1344, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1775750400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于CNN-BiLSTM模型的致密砂岩储层孔隙度预测方法
李黎 , 董政 , 侯凯 , 吴成 , 彭己君
物探与化探 | 方法研究·信息处理·仪器研制 2026,50(2): 319-329
收起
收藏切换
物探与化探 |方法研究·信息处理·仪器研制 2026 , 50 (2) : 319 -329
基于CNN-BiLSTM模型的致密砂岩储层孔隙度预测方法
全屏
[Author(id=1327707274996462304, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lili12@cnooc.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275097125602, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707274996462304, language=EN, stringName=Li LI, firstName=Li, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707275197788899, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707274996462304, language=CN, stringName=李黎, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio={"content":"

李黎(1981−),女,硕士研究生学历,高级工程师,主要从事油藏地球物理研究工作。Email:

"}, bioImg=null, bioContent=

李黎(1981−),女,硕士研究生学历,高级工程师,主要从事油藏地球物理研究工作。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707275264897765, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275344589543, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275264897765, language=EN, stringName=Zheng DONG, firstName=Zheng, middleName=null, lastName=DONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707275420087016, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275264897765, language=CN, stringName=董政, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707275495584490, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275604636396, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275495584490, language=EN, stringName=Kai HOU, firstName=Kai, middleName=null, lastName=HOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707275675939565, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275495584490, language=CN, stringName=侯凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707275747242735, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707275835323121, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275747242735, language=EN, stringName=Cheng WU, firstName=Cheng, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707277513044722, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707275747242735, language=CN, stringName=吴成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])]), Author(id=1327707277592736500, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327707277697594102, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707277592736500, language=EN, stringName=Ji-Jun PENG, firstName=Ji-Jun, middleName=null, lastName=PENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327707277802451703, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, authorId=1327707277592736500, language=CN, stringName=彭己君, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327707274904187612, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, xref=null, ext=[AuthorCompanyExt(id=1327707274916770525, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China), AuthorCompanyExt(id=1327707274925159134, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327707271020262081, companyId=1327707274904187612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中海石油(中国)有限公司 深圳分公司,广东 深圳 518000)])])]
李黎 , 董政, 侯凯, 吴成, 彭己君
作者信息
  • 中海石油(中国)有限公司 深圳分公司,广东 深圳 518000
作者简介:

李黎(1981−),女,硕士研究生学历,高级工程师,主要从事油藏地球物理研究工作。Email:

A CNN-BiLSTM model-based porosity prediction method for tight sandstone reservoirs
Li LI , Zheng DONG, Kai HOU, Cheng WU, Ji-Jun PENG
Affiliations
  • Shenzhen Branch of CNOOC Ltd., Shenzhen 518000, China
出版时间: 2026-04-10 doi: 10.11720/wtyht.2026.1344
文章导航
收藏切换

孔隙度是描述储层物理性质的重要参数,孔隙度预测的准确性对油气勘探开发、油气藏地质建模和精细评价具有重要意义。针对致密砂岩储层低孔、低渗及非均质性强的特点,本文提出一种融合卷积神经网络(convolutional neural network,CNN)和双向长短期记忆网络(bidirectional long short-term memory, BiLSTM)的储层孔隙度预测模型,用于从测井数据中提取特征并建立其与孔隙度参数之间的复杂非线性关联。首先,依据岩石物理模型筛选出与孔隙度显著相关的敏感弹性参数作为输入参数,随后借助卷积神经网络提取反演数据中的空间依赖特征,进一步通过双向长短时记忆神经网络捕捉其前后的时序依赖关系,最终实现孔隙度的有效预测。开平凹陷A油田3口井的测试结果表明,相比常规深度学习方法,CNN-BiLSTM模型的孔隙度预测结果具有更好的精度及横向分辨率,验证了该模型的有效性。在此基础上,利用该模型开展三维储层孔隙度预测,通过输入储层反演获得的弹性参数数据体计算出孔隙度数据体,为海上开平凹陷A油田少井区储层孔隙度预测提供了新的研究思路。

开平凹陷  /  CNN-BiLSTM模型  /  深度学习  /  孔隙度预测  /  致密砂岩

Porosity is a critical parameter for characterizing reservoir physical properties. The accuracy of porosity prediction holds significant implications for hydrocarbon exploration and production, as well as the geological modeling and fine-scale evaluation of hydrocarbon reservoirs. Considering the characteristics of tight sandstone reservoirs, such as low porosity, low permeability, and strong heterogeneity, this study proposed a reservoir porosity prediction model that integrates the convolutional neural network (CNN) and bidirectional long short-term memory(BiLSTM). The CNN-BiLSTM model is used to extract features from log data and establish complex nonlinear correlations between these features and porosity parameters. First, using petrophysical models, sensitive elastic parameters, which are significantly correlated with porosity, are selected as input parameters. Second, the spatially dependent features are extracted from the inversion data using the CNN. Third, the temporal dependencies throughout the data sequence are captured by BiLSTM. These processes contribute to effective porosity prediction. The test results of three wells in oilfield A, Kaiping sag, demonstrate that compared to conventional deep learning methods, the CNN-BiLSTM model achieved higher accuracy and lateral resolution in porosity prediction, verifying its effectiveness. Furthermore, the CNN-BiLSTM model was applied for the 3D reservoir porosity prediction by calculating the porosity data volume from elastic parameter volumes obtained through reservoir inversion. Overall, this study provides a novel approach for predicting reservoir porosity in the sparse well area of oilfield A, offshore Kaiping sag.

Kaiping sag  /  CNN-BiLSTM model  /  deep learning  /  porosity prediction  /  tight sandstone
李黎, 董政, 侯凯, 吴成, 彭己君. 基于CNN-BiLSTM模型的致密砂岩储层孔隙度预测方法. 物探与化探, 2026 , 50 (2) : 319 -329 . DOI: 10.11720/wtyht.2026.1344
Li LI, Zheng DONG, Kai HOU, Cheng WU, Ji-Jun PENG. A CNN-BiLSTM model-based porosity prediction method for tight sandstone reservoirs[J]. Geophysical and Geochemical Exploration, 2026 , 50 (2) : 319 -329 . DOI: 10.11720/wtyht.2026.1344
储层孔隙度是油气藏评价的基础,是描述储层特性、油气藏地质建模和油气藏精细化描述的重要参数。在目前的油气田勘探开发中,孔隙度主要依靠直接测定和间接解释两类方法测定。直接测定法包括井壁取心和岩心实验分析等技术手段,虽然结果较为准确,但通常作业周期长、成本高昂,需要投入大量人力与物力资源[1]。由于实际环境和成本的影响,所获得的岩石样品数据往往简单而狭窄,只能对孤立点进行评估,难以准确估计整个工区的孔隙度。间接解释法是通过测井数据估计储层参数(如孔隙度和渗透率)的技术手段[2]。该类方法通常依赖回归分析或经验公式。然而,实际储层结构复杂,非均质性强,测井数据易受噪声和异常值干扰,这些因素常会对模型的预测性能造成影响[3]。因此,传统手段已难以满足当前对孔隙度预测的精度与效率要求。近年来深度学习在非线性回归任务中展现出显著优势,引起广泛研究关注。该方法通过构建深层网络结构,融合多维度特征,能够有效挖掘变量间复杂的非线性关联。
在储层参数预测过程中,关键挑战在于如何充分利用地质与测井等多种资料,有效构建能够准确反映孔隙度、渗透率和饱和度等目标参数复杂非线性特征的响应模型[4]。近年来,已有诸多研究成功将深度学习引入储层参数预测任务中。陈蓉等[5]首先确定储层参数与测井响应之间的非线性映射关系,再通过BP神经网络准确预测储层的孔隙度和渗透率。严禛等[6]构建BP神经网络,辅之以细菌觅食算法进行储层预测,证明即使是在地震属性变化复杂的情况下,也能够实现高精度的收敛。郑宇哲等[7]通过无监督学习对模型进行初步训练,再利用有监督学习进行优化调整,从而显著提高了孔隙度预测的准确性。朱林奇等[8]通过预训练深度置信网络,再结合核极限学习机,最终输入T2谱预测渗透率,发现准确率和训练速度都得到了提高。段友祥等[9]构建两种卷积神经网络模型预测孔隙度,单层卷积模型用来训练,双层卷积模型用来预测,预测效果较好。付超等[10]提出了一种结合卷积神经网络和支持向量机的深度学习方法,通过剔除异常值、构建隐藏层提取油气特征,并利用优化后的样本进行预测,成功应用于HG地区碳酸盐岩油气储层预测。Hamidi等[11]设计了一种基于BP神经网络(BP-ANN)的方法,利用伊朗西南部Parsi油田的测井数据预测油藏岩心孔隙度,通过与Geolog软件的结果对比,发现BP-ANN在确定油藏孔隙度方面更准确,并最终在缺乏岩心数据的其他3口井中进行了孔隙度模拟。王冉[12]提出两种预测模型,其中SSA-BiGRU着力于孔隙度预测,1DCNN-BiGRU用来预测渗透率,通过优化超参数和融合卷积神经网络,显著提高了预测精度。Wang等[13]构建了一维卷积神经网络结合双向循环神经网络预测孔隙度,前者捕获测井数据的局部与层次特征,后者负责捕捉随深度变化的规律及上下文关联,最终取得良好效果。邵蓉波等[14]构建异架构的多任务神经网络模型用于预测储层参数,实验结果对比,异架构多任务预测模型效果好于单任务模型。赵军等[15]通过灰色关联方法优选渗透率敏感参数,并结合DBN在监督学习中的优化能力建立了渗透率预测模型,预测精度得到了提高。王俊等[16]构建DBRNN网络模型以建立孔隙度与测井数据之间的关系,从而准确预测孔隙度。王丽君[17]将SQ-Transformer和BGRU进行结合,分别实现了提取横向信息和融合获得孔隙度特征,保证孔隙度预测精度的同时还降低了内存占用。徐颖晋[18]结合CNN和Transformer并加入自注意力机制构建新型神经网络结构,提高了砂岩储层孔隙度预测的准确率。孙婉峰[19]提出在Transformer的基础上利用GRU处理序列数据的能力构建新模型,在运行效率提高的情况下,预测精度和其泛化性也得到了保证。以往学者已就预测孔隙度的问题,提出了不同的见解,但针对于珠江口盆地开平凹陷低孔低渗致密砂岩的孔隙度预测还未能提出有效可行的方法。
考虑到开平凹陷地层复杂、非均质性强、特征提取困难、预测难度较大的问题,本文提出了一种基于CNN和BiLSTM的孔隙度预测方法。首先,基于测井岩石物理模型选取与孔隙度相关性较高的敏感弹性参数,再通过卷积神经网络挖掘不同弹性参数间的空间相关性,将处理后的数据作为整体传入双向长短时记忆神经网络中进一步提取时序特征,构建出弹性参数数据和孔隙度数据的关系模型,并在KPA1井上进行孔隙度预测,与常规深度学习方法CNN和LSTM进行对比,证明CNN-BiLSTM模型的孔隙度预测结果具有更好的精度,验证该模型的有效性。在此基础上,利用该模型开展三维储层孔隙度预测,通过输入储层反演获得的弹性参数数据体计算出孔隙度数据体,为海上开平凹陷A油田少井区储层孔隙度预测提供了新的研究思路。
开平凹陷地处南海北部珠江口盆地珠二凹陷的西侧,北接神狐暗沙隆起,东邻云开低凸起,西连顺德凹陷,南抵顺鹤隆起带,面积约为5000 km2,现今水深为200~500 m。开平凹陷整体呈NEE向展布,内部发育多个隆起,进一步将其划分为西洼、西南洼、主洼、北洼和东洼共5个次级洼陷,其中,主洼规模最大、埋深最深。图1为珠江口盆地开平凹陷地理位置。开平凹陷A油田位于开平凹陷的主体部位,海域水深340 m,其主力油藏位于古近系文昌组和恩平组,纵向上可划分出30个单元,油藏类型以边水油藏为主[20]。
开平凹陷A油田古近系主要目的层恩平组,储层以含砾中—粗砂岩为主,少量砂砾岩和中、细砂岩,两个井区储层物性特征如下:
KPA1井区砂层厚度在2.8~50.8 m,储层厚度1.0~31.1 m;岩心分析孔隙度分布在9.0%~16.0%,中值12.4%,渗透率分布在1.0~74.4 mD,中值3.7 mD;测井解释孔隙度分布在10.7%~16.4%,中值12.7%,渗透率分布在1.0~31.6 mD,中值7.7 mD,属于低孔、低渗储层。
KPA2井区砂层厚度在9.6~86.2 m,储层厚度1.5~18.9 m;岩心分析孔隙度分布8.9%~15.3%,中值11.6%,渗透率分布在1.1~119.7 mD,中值2.9 mD;测井解释孔隙度分布在10.2%~13.4%,中值10.7%,渗透率分布在1.1~7.3 mD,中值1.2 mD,属于低孔、特低渗储层。油田各油层测井解释孔隙度中值11.8%,渗透率中值3.3 mD,储层属于低孔特低渗储层。图2为开平A油田恩平组物性特征。
研究过程中采用的孔隙度及弹性参数等井曲线数据来自开平A油田的3口井,目的层为321-345段,研究井分别为KPA1井、KPA3井和KPA2井,其在321-345层段的深度分别为3500.2~3714.8 m、3537.8~3780 m和3511~3745 m。该区块为低孔低渗储层,储层孔隙度介于9.5%~15.2%。通过叠前振幅随偏移距变化(amplitude versus offset,AVO)反演获得敏感弹性参数数据体,包括纵波阻抗(AI)、剪切阻抗(SI)、拉梅阻抗(LAMRHO)、剪切模量(UU)、剪切阻抗(UURHO)、体积模量(KK)、杨氏模量(EE)、泊松比(VV)、纵横波速度比(Vp/Vs)等多种敏感的叠前地震弹性参数数据体。
为定量表征该层段岩石物理参数的总体特征与分布规律,对KPA1井的测井数据进行了描述性统计分析,结果如表1所示。表中各项统计指标的含义如下:count代表参与统计的样本数量;mean(平均值)反映了参数的集中趋势或典型水平;std(标准差)衡量了数据围绕均值的离散程度,其值越大表明非均质性可能越强;min与max分别给出了参数的变化范围;25%、50%(中位数)和75%为四分位数,共同描述了数据的分布形态,其中中位数对极端值不敏感,能更稳健地反映数据的中心位置。
孔隙度受多种因素共同影响,为降低维度灾难风险,减轻模型训练负担并减少预测误差,需系统分析孔隙度与各类弹性参数之间的相关性。在此基础上,选取与孔隙度有密切关联的数据,按样本客观条件和预测精度要求筛选出和孔隙度相关性较强的弹性参数数据,建立适用于孔隙度预测的输入数据集。
针对主力油层,基于岩石物理模型,根据原始孔隙度,增减孔隙度值,模拟不同孔隙分数条件下的地震响应,进一步分析弹性参数的变化特征。图3为改变孔隙度条件下的弹性参数正演模拟曲线。从左到右,轨迹曲线依次为纵波阻抗、横波阻抗、剪切阻抗、体积模量、泊松比、杨氏模量、纵横波速度比、拉梅阻抗和剪切模量。每道的深蓝色曲线代表原始孔隙度曲线,红色曲线表示孔隙度增加2%,绿色曲线表示孔隙度增加4%,浅蓝色曲线表示孔隙度减小2%,紫色曲线表示孔隙度减小4%的正演曲线。如图3所示,随着孔隙度的增大,纵横波速度比与泊松比表现为上升趋势;而纵波阻抗、横波阻抗、剪切阻抗、体积模量、杨氏模量、拉梅阻抗及剪切模量则均呈现下降趋势。不同弹性参数对孔隙度变化的响应程度存在明显差异。
为了进一步量化孔隙度的敏感弹性参数,构建了各弹性参数随孔隙度变化的相对变化曲线,如图4所示。图4中曲线为改变孔隙度大小时各个弹性参数的相对变化量,弹性参数的变化量越大,图中曲线斜率越大,反映对孔隙度越敏感。从图4中可以看出,对孔隙度敏感程度的参数的顺序为剪切阻抗、拉梅阻抗、剪切模量、杨氏模量、体积模量、横波阻抗、纵波阻抗、泊松比、纵横波速度比。最终选定剪切阻抗、拉梅阻抗、剪切模量和杨氏模量为孔隙度敏感弹性参数,即作为预测孔隙度的输入数据。
如果将不同类型的弹性参数直接输入于模型训练,可能会因为量纲差异和数值尺度不一致的原因降低孔隙度预测的精度。为消除量纲不一致对模型性能的干扰,本文对所有特征数据进行了归一化处理,以减少不同特征之间的量级差异,使各特征在训练过程中具有相当的权重分布,从而提升模型的稳定性和预测准确性。所采用的最大—最小值归一化方法将原始数据线性变换至[0,1]区间。其公式如下:
$ {x}_\text{1}=\frac{x-{x}_\text{min}}{x-{x}_\text{max}} ,$
式中:$ {x}_\text{max}\mathrm{和}{x}_\text{min} $分别表示输入数据的最大值和最小值;x1为归一化数据;x为原始数据。
本文使用决定系数(R2)和均方根误差(RMSE)作为模型性能的评估指标。R2用于量化预测值与真实值之间的相关程度,其值越接近于1,表示变量间的相关性越高。作为一个无单位分数,R2可以客观反映模型的拟合程度,因为其排除了原始数据离散程度的干扰[19]。RMSE用以衡量预测值和实际值之间的偏差,RMSE值越小,代表模型预测精度越高。RMSE突出误差对总体评估的影响,采用RMSE作为评价标准可以避免极端误差影响整体评估的情况[21]。综上所述,选择RMSE和R2作为评价指标,可以量化模型的适用性。这两个指标计算公式为:
$ {R}^{2}=1-\frac{\displaystyle\sum \limits_{{i}=1}^{{n}}{\left({y}_{i}-{\widehat{y}}_{i}\right)}^{2}}{\displaystyle\sum \limits_{i=1}^{n}{\left({y}_{i}-{\overline{y}}_{i}\right)}^{2}} ,$
$ {RMSE}=\sqrt{\frac{1}{{n}}\sum \limits_{{i}=1}^{{n}}{\left({y}_{i}-{\widehat{y}}_{i}\right)}^{2}} , $
式中:n表示样本个数;$ {y}_{i} $表示样本真实值;$ {\widehat{y}}_{i} $表示样本预测值;$ {\overline{y}}_{i} $表示样本平均值。
卷积神经网络(CNN)作为深度学习中具有代表性的算法之一,其结构设计受到生物视觉感知机制的启发,能够适用于监督学习或非监督学习任务,该网络通过局部连接、共享卷积核参数以及池化操作,有效降低了模型的复杂度,并增强了计算效率和容错性能,目前已广泛应用于地质、地震及测井等地球物理领域[22]。典型的CNN结构通常包含输入层、卷积层、池化层、全连接层和输出层等结构(图5),其最显著的特点在于采用了局部连接和权重共享机制,这不仅大幅减少了模型参数,还增强了特征的提取能力。该网络能够自动、高效地学习输入数据中的层次化特征表示,并在深层网络中对原始信息进行高度抽象的处理,从而有效捕获数据内部的复杂模式[23]。随着CNN的发展,虽然卷积网络的基本结构几乎相同,但也演变出了许多变体。其中在时序数据处理中,卷积神经网络在时间序列预测中的应用,基于其一维卷积核能够捕捉输入序列中局部时间段内的依赖关系和变化模式,从而依据历史数据的动态特征进行预测。此外,池化操作的引入有助于压缩特征表示,在减少冗余和噪声的同时保留重要信息。由于本文的实验数据主要是基于序列数据,所以我们使用了一维卷积结构。
在内部神经网络层中,卷积层用于从输入数据中提取局部特征,通过卷积核进行多层卷积运算,并借助如ReLU与Leaky-ReLU等激活函数为模型引入非线性变换能力。池化层则对卷积所得特征进行聚合,通常采用最大池化或平均池化等方法实现数据降维,从而增强特征表达的鲁棒性。
Hochreiter等[24]于1997年提出了长短期记忆神经网络,图6是LSTM(long short-term memory)网络的单元结构示意。作为循环神经网络(recurrent neural network, RNN)的一种变体,LSTM延续了其链式序列结构,但在内部机制上存在显著差异。不同于RNN中单一的神经网络层结构,LSTM引入了3个门控机制——输入门、遗忘门和输出门,通过这些门结构动态调控细胞状态 ct 中信息的保留与遗忘比例。该机制使LSTM能够有效捕捉长期依赖关系,克服了RNN在训练过程中容易出现的梯度消失和梯度爆炸问题,从而具备更优的序列建模能力,能够更好地提取反演资料的时空特征信息,并将其应用于储层孔隙度预测[25]。
双向长短期记忆网络(BiLSTM)是在双向循环神经网络(bidirectional recurrent neural network, Bi-RNN)和LSTM基础上发展而来的一种结构。Bi-RNN中,每个训练序列均通过前向与后向两个独立的RNN进行处理,两者方向相反但共同连接至同一输出层;前向与后向隐含层之间保持独立,无信息交互,从而确保计算图的无环性。然而,Bi-RNN在反向传播过程中易出现梯度爆炸及信息失真等问题。为此,BiLSTM被提出以缓解上述缺陷,其在有效应对梯度不稳定性的同时,还具备较强的时间序列建模能力,适用场景广泛[26]。
在LSTM网络中,时序数据信息的传输都是按照时间由前向后单方向的进行,但是类似于孔隙度这种时序信息的特征不仅仅包含某个时刻的某个点,更与前后时刻的状态息息相关。因此,在本文研究中,为准确捕捉孔隙度沿深度方向与其上下地层之间的关联性,采用了BiLSTM网络。与仅能单向传递信息的LSTM不同,BiLSTM(结构如图7所示)是一种结合了正向与反向传播的双向循环神经网络,这一机制使模型能够更全面地理解地层序列中的上下文信息,因此特别适用于如孔隙度这类需综合考量上下地层关系的预测任务[27]。
CNN-BiLSTM(convolutional neural network-bidirectional long short-term memory)网络模型融合了CNN高效的数据空间提取能力和BiLSTM较强的序列信息建模优势,利用CNN-BiLSTM网络模型建立反演参数与储层孔隙度的映射关系(图8)。该模型将通过CNN层获取的空间特征信息输入BiLSTM,网络根据CNN提取的空间特征获取时空特征。模型中各层的描述如下:
1)输入层。将弹性参数数据进行数据预处理后输入到孔隙度预测模型中。
2) CNN层。这一层主要提取输入序列的特征。经过一维卷积和最大池化处理后,将原始数据映射到隐藏层的特征空间,构建全连接层的结构将其转化为输出,然后提取特征信息。
3)BiLSTM层。将获取的空间特征信息输入到BiLSTM中,BiLSTM层获取CNN层提取的特征。本文构建了两层BiLSTM结构,以充分理解测井数据的特征,捕捉测井数据的内部时空特征。
4)输出层。该层获得孔隙度的预测值。
为构建用于训练的样本集,选取KPA1、KPA2和KPA3井中与孔隙度显著相关的弹性参数曲线(包括剪切阻抗、拉梅阻抗、剪切模量及杨氏模量)作为输入变量,并以孔隙度曲线作为输出标签。随后,从总样本中随机划分20%作为验证集,用于后续对网络模型结构的调优。
超参数设置如下:CNN隐藏层数为2层,每层有64个大小为4的一维卷积核,每层有一个大小为2的一维maxpooling核;BiLSTM隐藏层数为2层,每层有40个隐藏单元,时间步长为5,批大小为10,学习率为0.001,max_Epochs设置为500。在监督过程的调优中,我们选择了具有自适应学习率的Adam优化算法。在训练模型时,应用Early stop防止过拟合并将dropout率设置为0.2,将早期停止epoch的个数设置为10。
按照上述深度神经网络参数对模型进行训练,对研究区KPA1井孔隙度进行预测。为了验证本文方法的优越性,将CNN-BiLSTM模型的孔隙度预测结果与CNN和LSTM模型进行效果比较,如图9所示。图9中蓝色曲线为实测孔隙度曲线,橙色曲线为深度学习模型预测曲线。从KPA1井的整体预测效果来看, CNN-BiLSTM模型所得到的孔隙度与实测孔隙度高度吻合,在低孔段(<10%)和中高孔段(>12%)均表现出更好的拟合效果,尤其在孔隙度变化剧烈层段,其预测曲线更贴近实测值,显示出更强的非线性拟合能力。而另外两种深度学习模型的预测结果则与原始曲线存在一定偏差。
为量化模型的预测效果,图10左列为模型预测值与真实值的交会图,右列为预测值与真实值之间误差的直方图。从图中能明显看出,相较于CNN和LSTM,CNN-BiLSTM模型的交会点更集中于对角线,误差直方图峰值更高且集中于0附近,说明其在不同孔隙度区间内均具有更稳定的预测性能。
为了进一步量化模型的预测效果,分别求取了3种方法预测结果相对于实测原始值的决定系数($ {R}^{2} $)和均方根误差(RMSE),如表2所示。由表2可知,相比于CNN和LSTM,CNN-BiLSTM网络模型预测孔隙度综合考虑了多种弹性参数与孔隙度之间的关系,模型拟合效果更为突出,误差更小,具有更强的预测能力和泛化能力。
为检验本文方法的有效性与应用价值,我们结合研究区实际地震资料进行了预测应用测试。测试所采用的输入数据为经由叠前振幅随偏移距变化(AVO)反演获得的弹性参数数据体,包括剪切阻抗、拉梅阻抗、剪切模量及杨氏模量(图11)。基于KPA1井的实际测井数据,此前已构建了用于孔隙度预测的CNN-BiLSTM模型,将上述叠前反演成果作为输入,导入已训练好的神经网络模型中,实现了研究区内孔隙度数据体的预测;该方法在横向上呈现出良好的连续性,能够清晰、准确地识别少井沉积区局部物源方向及有利储层平面展布(图12)。恩三段储层砂体的孔隙度主要介于8%~16%之间,且以11%左右为主(图12);以A层为例,KPA1井多为富油砂砾岩、含砾粗砂岩为主,表现为明显的水下分流河道微相沉积特征。孔隙度反演属性平面图可以看出,对应KPA1井为暖色区域,反演属性值在10%~15%之间;KPA3井周边多为荧光细砂岩,泥质含量高,表现为席状砂沉积微相特征,对应孔隙度反演属性值在5%~8%之间;过KPA2、KPA1顺物源方向,反演储层孔隙度较高(可达12%),显示出较好的物性条件,为有利储层分布区;高孔隙度区域(>12%)主要沿高部位及砂体叠置区呈条带状展布。结果表明,采用深度学习手段预测孔隙度具备可行性,有助于提升储层孔隙度预测的精度与分辨率,为少井区储层评价及井位部署提供了可靠依据,具有良好的应用前景。
1)本文提出的CNN-BiLSTM网络模型融合了卷积神经网络(CNN)高效的数据空间提取能力和双向长短期记忆网络(BiLSTM)对序列信息的有效捕捉与构建能力,使得CNN-BiLSTM模型能够处理多种输入数据并进行预测任务,并更准确地学习和表征复杂的弹性参数资料与孔隙度之间的关联,不仅提高了孔隙度的预测精度,而且节约了时间成本。
2)测试表明,CNN-BiLSTM模型的孔隙度预测效果要优于CNN和LSTM模型,决定系数($ {R}^{2} $)较CNN和LSTM模型分别提升了9.62%和2.97%,均方根误差(RMSE)较CNN和LSTM模型分别降低了27.66%和7.27%。结果表明该模型能够获得较高精度的孔隙度,模型的可靠性较好。该模型在开平凹陷A油田表现出良好的适用性,未来可进一步拓展至其他复杂储层类型如碳酸盐岩、页岩等验证其泛化能力。结合自注意力机制、图神经网络等结构,有望进一步提升模型在非均质性强储层预测中的精度。

参考文献 引证文献
排序方式:
1
杨柳青, 查蓓, 陈伟. 基于深度神经网络的砂岩储层孔隙度预测方法[J]. 中国科技论文, 2020, 15(1): 73−80.
Yang L Q, Zha B, Chen W. Prediction method of reservoir porosity based on deep neural network[J]. China Sciencepaper, 2020, 15(1): 73−80.
2
汪锐, 李芳, 刘仕友, 等. 岩石物理建模引导的低渗储层参数预测方法[J]. 煤田地质与勘探, 2024, 52(8): 187−197.
Wang R, Li F, Liu S Y, et al. A petrophysical modeling-guided method for predicting parameters of low-permeability reservoirs[J]. Coal Geology & Exploration, 2024, 52(8): 187−197.
3
Saito H, Kato M. Machine learning technique to find quantum many-body ground states of bosons on a lattice[J]. Journal of the Physical Society of Japan, 2018, 87(1): 014001.
4
Mahdy A, Zakaria W, Helmi A, et al. Machine learning approach for core permeability prediction from well logs in Sandstone Reservoir, Mediterranean Sea, Egypt[J]. Journal of Applied Geophysics, 2024, 220: 105249.
5
陈蓉, 王峰. 基于MATLAB的BP神经网络在储层物性预测中的应用[J]. 测井技术, 2009, 33(1): 75−78.
Chen R, Wang F. Application of MATLAB-based of BP neural network in reservoir parameters prediction[J]. Well Logging Technology, 2009, 33(1): 75−78.
6
严禛, 伍星蓉. 基于BFO-BP神经网络的储层预测研究[J]. 能源与环保, 2017, 39(7): 210−213.
Yan Z, Wu X R. Study on BFO-BP neural network to reservoir thickness prediction[J]. China Energy and Environmental Protection, 2017, 39(7): 210−213.
7
郑宇哲, 叶朝辉, 刘西恩, 等. 基于深度学习的储层物性参数预测方法研究[J]. 电子世界, 2018(4): 23−26.
Zheng Y Z, Ye Z H, Liu X E, et al. Research on prediction method of reservoir physical properties based on deep learning[J]. Electronics World, 2018(4): 23−26.
8
朱林奇, 张冲, 周雪晴, 等. 融合深度置信网络与与核极限学习机算法的核磁共振测井储层渗透率预测方法[J]. 计算机应用, 2017, 37(10): 3034−3038.
Zhu L Q, Zhang C, Zhou X Q, et al. Nuclear magnetic resonance logging reservoir permeability prediction method based on deep belief network and kernel extreme learning machine algorithm[J]. Journal of Computer Applications, 2017, 37(10): 3034−3038.
9
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.
Duan Y X, Li G T, Sun Q F. Application of convolutional neural network in reservoir prediction[J]. Journal on Communications, 2016, 37(S1): 1−9.
10
付超, 林年添, 张栋, 等. 多波地震深度学习的油气储层分布预测案例[J]. 地球物理学报, 2018, 61(1): 293−303.
Fu C, Lin N T, Zhang D, et al. Prediction of reservoirs using multi-component seismic data and the deep learning method[J]. Chinese Journal of Geophysics, 2018, 61(1): 293−303.
11
Hamidi H, Rafati R. Prediction of oil reservoir porosity based on BP-ANN[C]//Malacca:2012 International Conference on Innovation Management and Technology Research, IEEE, 2012: 241-246.
12
王冉. 基于深度学习的储层参数预测系统研究[D]. 大庆: 东北石油大学, 2023.
Wang R. Research on reservoir parameter prediction system based on deep learning[D]. Daqing: Northeast Petroleum University, 2023.
13
Wang J, Cao J X, Yuan S. Deep learning reservoir porosity prediction method based on a spatiotemporal convolution bi-directional long short-term memory neural network model[J]. Geomechanics for Energy and the Environment, 2022, 32: 100282.
14
邵蓉波, 肖立志, 廖广志, 等. 基于多任务学习的测井储层参数预测方法[J]. 地球物理学报, 2022, 65(5): 1883−1895.
Shao R B, Xiao L Z, Liao G Z, et al. Multitask learning based reservoir parameters prediction with geophysical logs[J]. Chinese Journal of Geophysics, 2022, 65(5): 1883−1895.
15
赵军, 张涛, 何胜林, 等. 基于参数优选的储层渗透率深度置信网络模型预测初探[J]. 油气藏评价与开发, 2021, 11(4): 577−585.
Zhao J, Zhang T, He S L, et al. Prediction of reservoir permeability by deep belief network based on optimized parameters[J]. Petroleum Reservoir Evaluation and Development, 2021, 11(4): 577−585.
16
王俊, 曹俊兴, 周欣. 基于深度双向循环神经网络的储层孔隙度预测[J]. 地球物理学进展, 2022, 37(1): 267−274.
Wang J, Cao J X, Zhou X. Reservoir porosity prediction based on deep bidirectional recurrent neural network[J]. Progress in Geophysics, 2022, 37(1): 267−274.
17
王丽君. 基于深度学习的储层孔隙度预测研究[D]. 青岛: 青岛理工大学, 2023.
Wang L J. Research on reservoir porosity prediction based on deep learning[D]. Qingdao: Qingdao University of Technology, 2023.
18
徐颖晋. 基于CNN-Transformer的致密砂岩储层参数预测研究[D]. 抚州: 东华理工大学, 2024.
Xu Y J. Research on tight sandstone reservoir parameter prediction based on CNN-Transformer[D]. Fuzhou: East China Institute of Technology, 2024.
19
孙婉峰. 基于Transformer的储层参数预测算法研究与应用[D]. 西安: 西安石油大学, 2025.
Sun W F. Research and application of reservoir parameter prediction algorithm based on Transformer[D]. Xi’an: Xi’an Shiyou University, 2025.
20
高阳东, 彭光荣, 陈兆明, 等. 珠江口盆地开平凹陷深水古近系勘探重大发现及意义[J]. 石油学报, 2023, 44(7): 1029−1040.
Gao Y D, Peng G R, Chen Z M, et al. Breakthrough and significance of deep-water Paleogene exploration in Kaiping Sag, Pearl River Mouth Basin[J]. Acta Petrolei Sinica, 2023, 44(7): 1029−1040.
21
刘怡伟. 基于深度神经网络的几类时间序列预测模型研究[D]. 大连: 大连海事大学, 2020.
Liu Y W. A research on several types of time series forecast models based on deep neural network[D]. Dalian: Dalian Maritime University, 2020.
22
古瑶, 解海军, 周子鹏, 等. 基于Attention机制的CNN-BiLSTM瞬变电磁实时反演方法[J]. 煤田地质与勘探, 2023, 51(10): 134−143.
Gu Y, Xie H J, Zhou Z P, et al. An Attention mechanism-based CNN-BiLSTM real-time transient electromagnetic method[J]. Coal Geology & Exploration, 2023, 51(10): 134−143.
23
李青, 张新燕, 马天娇, 等. 基于SSA-CNN-BiGRU-Attention的超短期风电功率预测模型[J]. 电机与控制应用, 2023, 50(5): 61−71.
Li Q, Zhang X Y, Ma T J, et al. Ultra-short term forecasting model of wind power based on SSA-CNN-BiGRU-attention[J]. Electric Machines & Control Application, 2023, 50(5): 61−71.
24
Hochreiter S, Schmidhuber J. Long short-term memory[J].Neural Comput.,1997, 9 (8): 1735-1780.
25
梁宏涛, 刘硕, 杜军威, 等. 深度学习应用于时序预测研究综述[J]. 计算机科学与探索, 2023, 17(6): 1285−1300.
Liang H T, Liu S, Du J W, et al. Review of deep learning applied to time series prediction[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(6): 1285−1300.
26
刘俊, 曹俊兴, 丁蔚楠, 等. 基于双向长短期记忆神经网络的储层孔隙度预测方法研究[J]. 地球物理学进展, 2022, 37(5): 1993−2000.
Liu J, Cao J X, Ding W N, et al. Research on reservoir porosity prediction method based on bidirectional longshort-term memory neural network[J]. Progress in Geophysics, 2022, 37(5): 1993−2000.
27
Yang N, Li G, Zhao P, et al. Porosity prediction from pre-stack seismic data via a data-driven approach[J]. Journal of Applied Geophysics, 2023, 211: 104947.
2026年第50卷第2期
95
43
0
引用本文
BibTeX
文章信息
doi: 10.11720/wtyht.2026.1344
  • 接收时间:2025-09-29
  • 首发时间:2026-11-12
  • 出版时间:2026-04-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-09-29
  • 修回日期:2026-01-21
  • 录用日期:2026-02-02
基金
作者信息
    中海石油(中国)有限公司 深圳分公司,广东 深圳 518000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/wtyht/CN/10.11720/wtyht.2026.1344
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏