Article(id=1327706966622842924, tenantId=1146029695717560320, journalId=1327236479169368089, issueId=1327706707108672154, articleNumber=null, orderNo=null, doi=10.11720/wtyht.2026.1283, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1756051200000, receivedDateStr=2025-08-25, revisedDate=1763049600000, revisedDateStr=2025-11-14, acceptedDate=null, acceptedDateStr=null, onlineDate=1794479608444, onlineDateStr=2026-11-12, pubDate=1770652800000, pubDateStr=2026-02-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794479608444, onlineIssueDateStr=2026-11-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794479608444, creator=13701087609, updateTime=1794479608444, updator=13701087609, issue=Issue{id=1327706707108672154, tenantId=1146029695717560320, journalId=1327236479169368089, year='2026', volume='50', issue='1', pageStart='1', pageEnd='187', issueExtLink='null', onlineDate='null', pubDate='1770652800000', pubDateStr='2026-02-10', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794479546572, creator='13701087609', updateTime=1794532672743, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327929534860603557, tenantId=1146029695717560320, journalId=1327236479169368089, issueId=1327706707108672154, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327929534860603558, tenantId=1146029695717560320, journalId=1327236479169368089, issueId=1327706707108672154, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=145, endPage=154, ext={EN=ArticleExt(id=1327706966853529645, articleId=1327706966622842924, tenantId=1146029695717560320, journalId=1327236479169368089, language=EN, title=River channel detection from 3D seismic data based on the attention mechanism of neural networks, columnId=null, journalTitle=Geophysical and Geochemical Exploration, columnName=null, runingTitle=null, highlight=null, articleAbstract=

The river channel sand detection can provide critical insights for hydrocarbon exploration, sediment transport, and paleofluvial geomorphology analysis. However, manual identification of river channels is time-consuming, cumbersome, and subjective, while traditional river channel detection methods based on attributes such as coherence cube and curvature are susceptible to noise and faults. In contrast, owing to powerful feature extraction and efficient feature representation capabilities, deep learning has been widely applied in seismic data processing. This paper proposed a river channel detection method using 3D seismic data and attention mechanisms in convolutional neural network (CNN). The method trained the constructed network using synthetic seismic data and river channel labels, achieving effective detection of river channels from test data and actual 3D seismic data. The proposed method is of great significance for achieving efficient and automated river channel detection during actual production.

, authors=Xiu-Peng SHI, Huan-Ju QIAN, Juan ZHANG, authorsList=Xiu-Peng SHI, Huan-Ju QIAN, Juan ZHANG, 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=1327706968845824066, articleId=1327706966622842924, tenantId=1146029695717560320, journalId=1327236479169368089, language=CN, title=基于注意力神经网络的三维地震数据河道检测方法, columnId=1327706089249943952, journalTitle=物探与化探, columnName=方法研究信息处理仪器研制, runingTitle=null, highlight=null, articleAbstract=

河道砂体检测在油气勘探、沉积物输运和古河流地貌分析等研究中发挥着重要作用 ,但由于人工识别河道耗时费力且主观性强,基于相干体、曲率等属性的传统河道检测方法易受噪声及断层影响。深度学习凭借其强大的特征提取能力和高效的特征表达能力,已广泛地应用于地震数据处理中。本文提出了一种基于注意力机制卷积神经网络的三维地震数据河道检测方法,使用人工合成地震数据以及河道标签对构建的网络进行训练,训练后的网络能够有效检测测试数据与实际三维地震数据中的河道,该方法对于实际生产工作中实现高效、自动化的河道检测具有重要意义。

, authors=时秀朋, 钱焕菊, 张娟, authorsList=时秀朋, 钱焕菊, 张娟, authorCompany=null, correspAuthors=null, authorNote=

时秀朋(1981−),女,汉族,2010年博士毕业于中国石油大学(华东)地质系,副研究员,主要从事地球物理勘探工作。Email:

, correspAuthorsNote=null, copyrightStatement=版权所有 © 2026 物探与化探编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=2lBC1Z5IVKTPRnd5GWKqkA==, magXml=dOQICvAQGcJGKDQqVVwq9Q==, pdfUrl=null, pdf=fx/OD8dysmrP5Mr3FV+8vA==, pdfFileSize=14148227, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=WcHVMMDkHXreAQAh9LmTag==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=TzIqXWHZcxxN9gTYDG5mrw==, mapNumber=null, fund=null)}, authors=[Author(id=1327706969177174087, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=shixiupeng.slyt@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327706969277837385, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969177174087, language=EN, stringName=Xiu-Peng SHI, firstName=Xiu-Peng, middleName=null, lastName=SHI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327706969378500682, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969177174087, language=CN, stringName=时秀朋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015, bio={"content":"

时秀朋(1981−),女,汉族,2010年博士毕业于中国石油大学(华东)地质系,副研究员,主要从事地球物理勘探工作。Email:

"}, bioImg=null, bioContent=

时秀朋(1981−),女,汉族,2010年博士毕业于中国石油大学(华东)地质系,副研究员,主要从事地球物理勘探工作。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327706969080705091, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, xref=null, ext=[AuthorCompanyExt(id=1327706969093288004, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China), AuthorCompanyExt(id=1327706969105870917, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015)])]), Author(id=1327706969449803852, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=1327706969512718414, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969449803852, language=EN, stringName=Huan-Ju QIAN, firstName=Huan-Ju, middleName=null, lastName=QIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327706969584021583, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969449803852, language=CN, stringName=钱焕菊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327706969080705091, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, xref=null, ext=[AuthorCompanyExt(id=1327706969093288004, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China), AuthorCompanyExt(id=1327706969105870917, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015)])]), Author(id=1327706969655324753, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=1327706969739210835, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969655324753, language=EN, stringName=Juan ZHANG, firstName=Juan, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327706969806319700, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969655324753, language=CN, stringName=张娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327706969080705091, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, xref=null, ext=[AuthorCompanyExt(id=1327706969093288004, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China), AuthorCompanyExt(id=1327706969105870917, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015)])])], keywords=[Keyword(id=1327706969898594389, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, orderNo=1, keyword=river channel detection from seismic data), Keyword(id=1327706969969897558, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1327706970032812119, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, orderNo=3, keyword=convolutional neural network(CNN)), Keyword(id=1327706970095726680, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, orderNo=4, keyword=synthetic data for training), Keyword(id=1327706970162835545, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, orderNo=5, keyword=attention mechanism), Keyword(id=1327706970221555802, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, orderNo=1, keyword=地震河道检测), Keyword(id=1327706970305441883, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1327706970372550748, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, orderNo=3, keyword=卷积神经网络), Keyword(id=1327706970448048221, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, orderNo=4, keyword=合成训练数据), Keyword(id=1327706970523545694, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, orderNo=5, keyword=注意力机制)], refs=[Reference(id=1327706973975457907, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=邓琳平, 丁峰, 林龙波, 等. 河流相砂体边界预测方法研究[J]. 海洋地质前沿, 2022, 38(3): 59−64., articleTitle=null, refAbstract=null), Reference(id=1327706974050955380, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=Deng L P, Ding F, Lin L B, et al. A review of prediction methods for fluvial sand boundary[J]. Marine Geology Frontiers, 2022, 38(3): 59−64., articleTitle=null, refAbstract=null), Reference(id=1327706974118064245, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=徐世东, 陈书平, 薛佳雯, 等. 井震数据联合驱动下砂体叠置模式构建技术及应用——以WX油田东北部姚家组葡萄花油层为例[J]. 石油地球物理勘探, 2023, 58(1): 178−189., articleTitle=null, refAbstract=null), Reference(id=1327706974206144630, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=Xu S D, Chen S P, Xue J W, et al. Construction technology of superimposition patterns of sandbodies driven by well-seismic data and its application: Taking the Putaohua reservoir of Yaojia Formation in the northeastern WX Oilfield as an example[J]. Oil Geophysical Prospecting, 2023, 58(1): 178−189., articleTitle=null, refAbstract=null), Reference(id=1327706974306807927, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=张运龙, 丁峰, 尹成, 等. 基于地震波形结构属性识别河流相砂体叠置区[J]. 石油学报, 2018, 39(7): 792−801., articleTitle=null, refAbstract=null), Reference(id=1327706974378111096, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Y L, Ding F, Yin C, et al. The identification of fluvial sand-body superimposed area based on seismic waveform structure attributes[J]. Acta Petrolei Sinica, 2018, 39(7): 792−801., articleTitle=null, refAbstract=null), Reference(id=1327706974457802873, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=任宪军, 李钟, 马应龙, 等. 地震分频迭代反演在薄层河道砂体预测中的应用[J]. 物探与化探, 2023, 47(2): 420−428., articleTitle=null, refAbstract=null), Reference(id=1327706974508134522, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren X J, Li Z, Ma Y L, et al. Application of seismic frequency-divided iterative inversion in the prediction of thinly laminated channel sand bodies[J]. Geophysical and Geochemical Exploration, 2023, 47(2): 420−428., articleTitle=null, refAbstract=null), Reference(id=1327706974566854779, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Marfurt K J, Sudhaker V, Gersztenkorn A, et al. Coherency calculations in the presence of structural dip[J]. Geophysics, 1999, 64(1): 104−111., articleTitle=null, refAbstract=null), Reference(id=1327706974629769340, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=Marfurt K J, Kirlin R L, Farmer S L, et al. 3-D seismic attributes using a semblance-based coherency algorithm[J]. Geophysics, 1998, 63(4): 1150−1165., articleTitle=null, refAbstract=null), Reference(id=1327706974713655421, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=Hart B S. Channel detection in 3-D seismic data using sweetness[J]. AAPG Bulletin, 2008, 92(6): 733−742., articleTitle=null, refAbstract=null), Reference(id=1327706974784958590, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu X M. Directional structure-tensor-based coherence to detect seismic faults and channels[J]. Geophysics, 2017, 82(2): A13−A17., articleTitle=null, refAbstract=null), Reference(id=1327706974843678847, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=何小龙, 张兵, 杨凯, 等. 基于沉积微相特征挖掘的随机森林岩石相测井识别方法——以新场地区须家河组二段致密砂岩为例[J]. 物探与化探, 2024, 48(5): 1337−1347., articleTitle=null, refAbstract=null), Reference(id=1327706974919176320, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=He X L, Zhang B, Yang K, et al. A log-based lithofacies identification method based on random forest and sedimentary microfacies characteristics: A case study of tight sandstones in the second member of the Xujiahe Formation in the Xinchang area[J]. Geophysical and Geochemical Exploration, 2024, 48(5): 1337−1347., articleTitle=null, refAbstract=null), Reference(id=1327706974998868097, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren S, He K, Girshick R, et al. Faster R-CNN: Towards realtime object detection with region proposal networks[J]. Advances in Neural Information Processing Systems, 2015: 91-99., articleTitle=null, refAbstract=null), Reference(id=1327706975095337090, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=唐杰, 韩盛元, 刘英昌, 等. 基于去噪卷积神经网络的面波噪声压制方法[J]. 石油物探, 2022, 61(2): 245−252., articleTitle=null, refAbstract=null), Reference(id=1327706976760475779, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang J, Han S Y, Liu Y C, et al. Seismic surface wave attenuation based on denoising convolutional neural networks[J]. Geophysical Prospecting for Petroleum, 2022, 61(2): 245−252., articleTitle=null, refAbstract=null), Reference(id=1327706976924053636, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen L C, Zhu Y K, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Computer Vision – ECCV 2018. Cham: Springer, 2018: 833-851., articleTitle=null, refAbstract=null), Reference(id=1327706976986968197, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Y Y, Lu P, Yu H, et al. Enhancement of seismic imaging: An innovative deep learning approach[EB/OL]. 2019: arXiv: 1909.06016. https://arxiv.org/abs/1909.06016., articleTitle=null, refAbstract=null), Reference(id=1327706977049882758, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Di H B, AlRegib G. A comparison of seismic saltbody interpretation via neural networks at sample and pattern levels[J]. Geophysical Prospecting, 2020, 68(2): 521−535., articleTitle=null, refAbstract=null), Reference(id=1327706977108603015, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=唐杰, 孟涛, 韩盛元, 等. 基于多分辨率U-Net网络的地震数据断层检测方法[J]. 石油地球物理勘探, 2021, 56(3): 436−445, 409., articleTitle=null, refAbstract=null), Reference(id=1327706977188294792, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang J, Meng T, Han S Y, et al. A fault detection method of seismic data based on MultiResU-Net[J]. Oil Geophysical Prospecting, 2021, 56(3): 436−445, 409., articleTitle=null, refAbstract=null), Reference(id=1327706977259597961, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang H, Song X H, Zhu P M, et al. A two-stage convolutional neural network for interactive channel segmentation from 3-D seismic data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5915915., articleTitle=null, refAbstract=null), Reference(id=1327706977314123914, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Pham N, Fomel S, Dunlap D. Automatic channel detection using deep learning[J]. Interpretation, 2019, 7(3): SE43−SE50., articleTitle=null, refAbstract=null), Reference(id=1327706977372844171, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Gramstad O, Goledowski B, Nickel M. Automated channel detection using deep convolutional neural networks[C]//San Antonio: SEG Technical Program Expanded Abstracts 2019, Society of Exploration Geophysicists, 2019: 2483-2487., articleTitle=null, refAbstract=null), Reference(id=1327706977435758732, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu X M, Liang L M, Shi Y Z, et al. FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation[J]. Geophysics, 2019, 84(3): IM35−IM45., articleTitle=null, refAbstract=null), Reference(id=1327706977507061901, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao H, Wu X M, Liu G F. ChannelSeg3D: Channel simulation and deep learning for channel interpretation in 3D seismic images[J]. Geophysics, 2021, 86(4): IM73−IM83., articleTitle=null, refAbstract=null), Reference(id=1327706977578365070, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang G Y, Wu X M, Zhang W. cigChannel: A large-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation[J]. Earth System Science Data, 2025, 17(7): 3447−3471., articleTitle=null, refAbstract=null), Reference(id=1327706977649668239, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang X K, Lou Y H, Liu N H, et al. 3-D UXSE-net for seismic channel detection based on satellite image enhanced synthetic datasets[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18: 8300−8311., articleTitle=null, refAbstract=null), Reference(id=1327706977708388496, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Nanson G C, Hickin E J. Channel migration and incision on the beatton river[J]. Journal of Hydraulic Engineering, 1983, 109(3): 327−337., articleTitle=null, refAbstract=null), Reference(id=1327706977771303057, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Howard A D, Knutson T R. Sufficient conditions for river meandering: A simulation approach[J]. Water Resources Research, 1984, 20(11): 1659−1667., articleTitle=null, refAbstract=null), Reference(id=1327706977842606226, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Sylvester Z, Durkin P, Covault J A. High curvatures drive river meandering[J]. Geology, 2019, 47(3): 263−266., articleTitle=null, refAbstract=null), Reference(id=1327706977922298003, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu X M, Geng Z C, Shi Y Z, et al. Building realistic structure models to train convolutional neural networks for seismic structural interpretation[J]. Geophysics, 2020, 85(4): WA27−WA39., articleTitle=null, refAbstract=null), Reference(id=1327706978043932820, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Li H Z, Ren Z H, Zhu G Q, et al. AE-UNet: A composite lung CT image segmentation framework using attention mechanism and edge detection[J]. The Journal of Supercomputing, 2024, 81(1): 331., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327706969080705091, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, xref=null, ext=[AuthorCompanyExt(id=1327706969093288004, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China), AuthorCompanyExt(id=1327706969105870917, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015)])], figs=[ArticleFig(id=1327706970636791903, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 1, caption=Synthetic seismic data and channel labels, figureFileSmall=g0bF0Ss+fIfisfXVbsxIGw==, figureFileBig=WcHVMMDkHXreAQAh9LmTag==, tableContent=null), ArticleFig(id=1327706972318707808, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图1, caption=人工合成地震数据及河道标签, figureFileSmall=g0bF0Ss+fIfisfXVbsxIGw==, figureFileBig=WcHVMMDkHXreAQAh9LmTag==, tableContent=null), ArticleFig(id=1327706972520034401, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 2, caption=Meandering river, figureFileSmall=OI0+mr1YyN4tPDv6MRpUkg==, figureFileBig=8KBSSg4zMHIMffQYeBZzbA==, tableContent=null), ArticleFig(id=1327706972587143266, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图2, caption=蜿蜒河流, figureFileSmall=OI0+mr1YyN4tPDv6MRpUkg==, figureFileBig=8KBSSg4zMHIMffQYeBZzbA==, tableContent=null), ArticleFig(id=1327706972775886947, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 3, caption=Cross-sections of U-shaped channel(a) and V-shaped channel(b), figureFileSmall=zmHmwWHBPTAMEfpvSeFfcg==, figureFileBig=tg2D+KMyodzTKxpKjSB6VQ==, tableContent=null), ArticleFig(id=1327706972851384420, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图3, caption=U型河道(a)和V型河道(b)截面, figureFileSmall=zmHmwWHBPTAMEfpvSeFfcg==, figureFileBig=tg2D+KMyodzTKxpKjSB6VQ==, tableContent=null), ArticleFig(id=1327706972935270501, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 4, caption=Seismic data and channel labels, figureFileSmall=pI/9MrGvJ5/oTmrc6t3oiA==, figureFileBig=UIHklWle2vQYMtkTOobXIA==, tableContent=null), ArticleFig(id=1327706973040128102, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图4, caption=地震数据及河道标签, figureFileSmall=pI/9MrGvJ5/oTmrc6t3oiA==, figureFileBig=UIHklWle2vQYMtkTOobXIA==, tableContent=null), ArticleFig(id=1327706973115625575, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 5, caption=Convolutional neural network structure for channel detection, figureFileSmall=BmMCeoJYpR0IvGidHZ88jw==, figureFileBig=AEmt0sVq81+wVx5ViWTwrQ==, tableContent=null), ArticleFig(id=1327706973195317352, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图5, caption=卷积神经网络结构河道检测, figureFileSmall=BmMCeoJYpR0IvGidHZ88jw==, figureFileBig=AEmt0sVq81+wVx5ViWTwrQ==, tableContent=null), ArticleFig(id=1327706973270814825, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 6, caption=The parameter changes during the training process, figureFileSmall=Y42OdH1/iU6mecU8NYgNlQ==, figureFileBig=wfSLR3Fi1pZbxFVFlV1tAg==, tableContent=null), ArticleFig(id=1327706973342117994, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图6, caption=训练过程中的参数变化, figureFileSmall=Y42OdH1/iU6mecU8NYgNlQ==, figureFileBig=wfSLR3Fi1pZbxFVFlV1tAg==, tableContent=null), ArticleFig(id=1327706973417615467, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 7, caption=Network correctness verification curve, figureFileSmall=Q4Pe6XDMpVhPh2tWnOHvMA==, figureFileBig=On2evEGfhQ+XGAjPlaPQfw==, tableContent=null), ArticleFig(id=1327706973493112940, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图7, caption=网络正确性验证曲线, figureFileSmall=Q4Pe6XDMpVhPh2tWnOHvMA==, figureFileBig=On2evEGfhQ+XGAjPlaPQfw==, tableContent=null), ArticleFig(id=1327706973564416109, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 8, caption=Comparison diagram of channel detection results for synthetic seismic data, figureFileSmall=AW4rCnQLZQ3DamNV74eSmQ==, figureFileBig=a8YDrQqMPqr2+/MKxk69Jw==, tableContent=null), ArticleFig(id=1327706973631524974, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图8, caption=合成地震数据河道检测结果对比, figureFileSmall=AW4rCnQLZQ3DamNV74eSmQ==, figureFileBig=a8YDrQqMPqr2+/MKxk69Jw==, tableContent=null), ArticleFig(id=1327706973694439535, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 9, caption=Channel detection results with different methods for the J2t32 horizon in the Junggar Basin 4 block, figureFileSmall=PGUGCz0JvGepX8kjDu4a/A==, figureFileBig=op8FAXnRYADkWwDwbWKHqw==, tableContent=null), ArticleFig(id=1327706973765742704, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图9, caption=准中4区块J2t32层位不同方法的河道检测结果, figureFileSmall=PGUGCz0JvGepX8kjDu4a/A==, figureFileBig=op8FAXnRYADkWwDwbWKHqw==, tableContent=null), ArticleFig(id=1327706973816074353, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=EN, label=Figure 10, caption=Prediction probability of channel sand body in J2t31 horizon, figureFileSmall=DFuFpxf7QlCSmO5dMUovwg==, figureFileBig=lhgpmPhW/SvOS3tWWBpXIQ==, tableContent=null), ArticleFig(id=1327706973878988914, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, language=CN, label=图10, caption=工区J2t31层位河道砂体预测概率, figureFileSmall=DFuFpxf7QlCSmO5dMUovwg==, figureFileBig=lhgpmPhW/SvOS3tWWBpXIQ==, tableContent=null)], 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.2026.1283, detailUrlEn=https://castjournals.cast.org.cn/joweb/wtyht/EN/10.11720/wtyht.2026.1283, pdfUrlCn=https://castjournals.cast.org.cn/joweb/wtyht/CN/PDF/10.11720/wtyht.2026.1283, pdfUrlEn=https://castjournals.cast.org.cn/joweb/wtyht/EN/PDF/10.11720/wtyht.2026.1283, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1770652800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于注意力神经网络的三维地震数据河道检测方法
时秀朋 , 钱焕菊 , 张娟
物探与化探 | 方法研究信息处理仪器研制 2026,50(1): 145-154
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 (1) : 145 -154
基于注意力神经网络的三维地震数据河道检测方法
全屏
[Author(id=1327706969177174087, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=shixiupeng.slyt@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327706969277837385, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969177174087, language=EN, stringName=Xiu-Peng SHI, firstName=Xiu-Peng, middleName=null, lastName=SHI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327706969378500682, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969177174087, language=CN, stringName=时秀朋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015, bio={"content":"

时秀朋(1981−),女,汉族,2010年博士毕业于中国石油大学(华东)地质系,副研究员,主要从事地球物理勘探工作。Email:

"}, bioImg=null, bioContent=

时秀朋(1981−),女,汉族,2010年博士毕业于中国石油大学(华东)地质系,副研究员,主要从事地球物理勘探工作。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327706969080705091, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, xref=null, ext=[AuthorCompanyExt(id=1327706969093288004, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China), AuthorCompanyExt(id=1327706969105870917, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015)])]), Author(id=1327706969449803852, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=1327706969512718414, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969449803852, language=EN, stringName=Huan-Ju QIAN, firstName=Huan-Ju, middleName=null, lastName=QIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327706969584021583, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969449803852, language=CN, stringName=钱焕菊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327706969080705091, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, xref=null, ext=[AuthorCompanyExt(id=1327706969093288004, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China), AuthorCompanyExt(id=1327706969105870917, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015)])]), Author(id=1327706969655324753, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, 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=1327706969739210835, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969655324753, language=EN, stringName=Juan ZHANG, firstName=Juan, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1327706969806319700, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, authorId=1327706969655324753, language=CN, stringName=张娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327706969080705091, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, xref=null, ext=[AuthorCompanyExt(id=1327706969093288004, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China), AuthorCompanyExt(id=1327706969105870917, tenantId=1146029695717560320, journalId=1327236479169368089, articleId=1327706966622842924, companyId=1327706969080705091, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015)])])]
时秀朋 , 钱焕菊, 张娟
作者信息
  • 中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015
作者简介:

时秀朋(1981−),女,汉族,2010年博士毕业于中国石油大学(华东)地质系,副研究员,主要从事地球物理勘探工作。Email:

River channel detection from 3D seismic data based on the attention mechanism of neural networks
Xiu-Peng SHI , Huan-Ju QIAN, Juan ZHANG
Affiliations
  • Exploration and Production Research Institute, Shengli Oilfield Company, Sinopec, Dongying 257015, China
出版时间: 2026-02-10 doi: 10.11720/wtyht.2026.1283
文章导航
收藏切换

河道砂体检测在油气勘探、沉积物输运和古河流地貌分析等研究中发挥着重要作用 ,但由于人工识别河道耗时费力且主观性强,基于相干体、曲率等属性的传统河道检测方法易受噪声及断层影响。深度学习凭借其强大的特征提取能力和高效的特征表达能力,已广泛地应用于地震数据处理中。本文提出了一种基于注意力机制卷积神经网络的三维地震数据河道检测方法,使用人工合成地震数据以及河道标签对构建的网络进行训练,训练后的网络能够有效检测测试数据与实际三维地震数据中的河道,该方法对于实际生产工作中实现高效、自动化的河道检测具有重要意义。

地震河道检测  /  深度学习  /  卷积神经网络  /  合成训练数据  /  注意力机制

The river channel sand detection can provide critical insights for hydrocarbon exploration, sediment transport, and paleofluvial geomorphology analysis. However, manual identification of river channels is time-consuming, cumbersome, and subjective, while traditional river channel detection methods based on attributes such as coherence cube and curvature are susceptible to noise and faults. In contrast, owing to powerful feature extraction and efficient feature representation capabilities, deep learning has been widely applied in seismic data processing. This paper proposed a river channel detection method using 3D seismic data and attention mechanisms in convolutional neural network (CNN). The method trained the constructed network using synthetic seismic data and river channel labels, achieving effective detection of river channels from test data and actual 3D seismic data. The proposed method is of great significance for achieving efficient and automated river channel detection during actual production.

river channel detection from seismic data  /  deep learning  /  convolutional neural network(CNN)  /  synthetic data for training  /  attention mechanism
时秀朋, 钱焕菊, 张娟. 基于注意力神经网络的三维地震数据河道检测方法. 物探与化探, 2026 , 50 (1) : 145 -154 . DOI: 10.11720/wtyht.2026.1283
Xiu-Peng SHI, Huan-Ju QIAN, Juan ZHANG. River channel detection from 3D seismic data based on the attention mechanism of neural networks[J]. Geophysical and Geochemical Exploration, 2026 , 50 (1) : 145 -154 . DOI: 10.11720/wtyht.2026.1283
河道砂岩储层是陆相盆地重要的油气储层,在非传统油气资源勘探中具有重要作用。作为沉积环境的重要指标,河道检测在河流相储层开发、沉积物输送及古河流地貌演化分析等方面至关重要[1-3]。河道代表了特定的沉积环境,识别河道有助于地质学家了解古河流系统的演化、沉积过程和沉积物搬运等信息。同时,河道还是油气聚集的关键区带,了解河流相的构造特征和沉积特性有助于预测储层特性和展布,为石油地质勘探和地质科学研究提供有价值的信息。地震资料可以提供与地质构造相关的三维视角,使地质学家能够准确地描述和理解地层的形态、展布和排列,有助于识别河道及其周围的地层状态。利用三维地震资料识别河道在石油地质勘探和地质科学研究等领域具有重要的实际意义和应用价值。
传统的河道解释通常需要手动解释,这不仅主观性较强,而且在地层构造复杂的地区容易出现错漏[4]。河道可以通过其不同于周围岩层的独特形状和沉积结构特征在地震数据体中识别出来,在地震数据中表现为不连续反射结构,以往通常使用地震属性(例如相干体[5]、相似性[6]和甜点[7]等)进行检测。地震属性是通过对地震数据进行数学变换而获得的地震波几何学、运动学、动力学和统计特征的特殊度量,地震属性通常可以表示地震波的一个或多个特征参数,突出地质体在某一方面的地球物理响应特征。其中相干体属性突出了地震不连续性,可以检测河道,但是相干性会受到噪声的影响,还可能受到断层等不连续性信息的干扰[8];振幅属性能够凸显波峰或波谷的反射强度,对砂岩体厚度等信息比较敏感;频率属性能够凸显地震频率的幅度和空间变化,有助于反映地层结构、沉积旋回、砂泥岩互层等。结合地震资料中的储层特征,选择合适的地震属性至关重要。地震属性可以有效地凸显某一方面的地球物理信息,增强地震资料的储层预测能力。然而,凸显某一方面的地球物理信息的同时,必然导致其他方面的地球物理信息的弱化甚至忽略,难以完整反映原有的地震信息。在地质构造复杂、地形复杂等地质条件下,地震属性提取方法可能受到限制,不完整或质量差的地震数据可能导致地震属性的精度和可靠性下降。此外,尽管河道是一种地质体,但以往的许多解释人员往往仅限于在地震数据体中逐层分析它们,无法有效地分析河道的空间分布。另外考虑到构造运动等因素导致地层变形,也增加了在地震数据体中解释河道砂体的复杂性[9]。
近年来,随着计算机运算能力的飞速提升,机器学习等人工智能方法得到了越来越多的应用,深度学习方法具有强大的特征提取能力和高效的特征表达能力,被广泛应用于图像分类、信号处理以及目标检测等领域[10-12]。深度学习在地球物理学研究中也被广泛地应用于增强地震成像效果[13]、盐体描绘[14]和断层检测[15]等工作之中,并取得了很好的效果。深度学习地震数据河道检测可以基于像素分类或语义分割原理进行检测[16]。Pham 等[17]将河道检测看作语义分割任务,标签数据是通过人工解释结果构建的,提出了一种用于自动检测三维地震体中河道的编码—解码卷积神经网络,取得了较好的河道检测效果。深度学习地震数据河道检测需要构建训练数据集,Gramstad等[18]使用来自人工解释的河道数据集训练了三维卷积神经网络。以往的研究表明,监督学习中的样本标记错误或不足会显著降低模型性能 [19]。为了解决这个问题,可以通过数值模拟过程生成合成地震数据集,Gao等[20]通过模拟蜿蜒河道生成了具有真实河道结构的合成训练数据集;Wang 等[21]给出了一种基于地质河道模拟和地球物理正演模拟生成大规模合成数据集的工作流程;Zhang等[22]基于卫星图像构建了河道砂体模型,并进行了河道检测。
本文提出了一种融合注意力机制的卷积神经网络的地震数据河道砂体检测方法。该方法利用人工合成的地震数据以及对应的河道砂体标签数据来训练并测试神经网络,在合成数据测试集与实际地震数据中都取得了很好的河道砂体检测结果。
为了训练深度学习网络,需要构建大量成对的地震数据及相应的河道标签。河道检测训练数据集可以使用实际地震数据和人工拾取的河道标签数据作为深度学习网络模型,然后将训练完备的网络模型应用于实际地震数据进行河道检测。然而实际数据往往包含复杂且未知的地质因素、噪声等的影响,实际数据标签通常依赖解释人员(地震解释、测井解释),不可避免地带有主观性与不确定性,而且标注范围有限。人工拾取河道标签解释工作量大、成本高,而合成数据相对可控,在人工合成数据中,河道形态、物性参数、噪声水平等都可以人为设定和控制。在人工构建河道数据标签时,标签是直接生成的,确保标签与数据完全一致;而且人工合成数据可生成大规模样本,也可以生成不同构型、不同噪声和参数的多组样本,满足深度学习对数据量的需求。
本文采用模拟方法合成地震数据及相应的河道标签,以此作为训练和测试数据集,可高效生成大量训练数据。合成地震数据及其相应的河道标签数据的过程如图1所示:首先,采用地质模拟或者河道卫星图像构建河道平面分布;其次,将河道与平层模型相结合(为模拟多期河道叠置,可以在多个地层中加入河道)形成立体分布河道;然后,加入褶皱弯曲等地质构造并创建反射率模型以及相应的河道标签;继而通过与子波卷积,生成合成地震数据体;最后,加入噪声以增强合成数据与实际数据的贴合度。
以往的研究表明,曲流河道会随着时间推移发生迁移,迁移持续进行导致弯曲曲率增加,最终导致河道截弯取直并形成牛轭湖。从地质过程正演模拟的河道提取中心线,中心线随机放置在网格上,并以随机角度旋转,获得河道的平面模型。
人工生成包含蜿蜒河流的合成地震数据的模拟方法为从相对笔直的河道开始,根据河流迁移速率迭代地迁移河道。经过迭代后,最初的直线河道逐渐演变为蜿蜒形式,最终模拟出蜿蜒河道。忽略河道宽度,它可以简化为由一系列均匀分布的节点组成的中心线。该中心线包含3段:上游、中游和下游。在整个模拟过程中,上游和下游河段保持不变,而中游河段则根据最初引入的随机扰动发生偏移变化。这种转变有助于河流模型从线性演变为蜿蜒河流[23]。河流的迁移速率与其弯道半径和宽度相关,名义迁移率R0表达式如下:
$ R_{_0}=\mathit{\mathrm{k}}_{_1}\cdot(W/R)\ , $
式中:W为河流的宽度;R表示河道中心线上各节点的曲率半径;k1为常数迁移率。在蜿蜒河流的演变过程中,不仅要考虑局部曲率,还要考虑上游河道的弯曲[24]。考虑了上游曲率的迁移率R1为:
$ R_1=\Omega R_0(s)+\Gamma\left[\int_0^{\infty}G(\xi)\mathrm{d}\xi\right]^{-1}\left[\int_0^{\infty}R_0(s-\xi)G(\xi)\mathrm{d}\xi\right]\ , $
式中:Ω和Γ是加权因子;s表示河流中心线的当前位置;ξ表示从当前位置到河流上游的距离;G(ξ)是一个指数加权函数,满足:
$ G(\xi)=\mathrm{e}^{-\alpha\xi}\ , $
$ \alpha=2\mathrm{k}C_f/D\ , $
式中:α为调整参数,是摩擦系数Cf和水深D的函数;k是一个常数。
计算河流演变过程中各节点沿河流中心线的偏移率,并利用更新后的偏移量计算出河流节点的新位置:
$ x_{i+1}=x_i+R_1\Delta t\frac{dy}{\sqrt{dx^2+dy^2+dz^2}}\ , $
$ y_{i+1}=y_i+R_1\Delta t\frac{dx}{\sqrt{dx^2+dy^2+dz^2}}\ , $
式中:xi和yi表示第i个更新;xi+1和yi+1表示第i+1个更新;Δt表示时间间隔;dx、dy、dz表示空间间距。在蜿蜒河流的演化过程中(图2),河岸持续的水流侵蚀和冲刷使河流曲率逐渐增大,最终导致局部河段变直,形成颈部截断和新河道的形成。为了模拟河流的这种变直现象,采用截断距离来限制蜿蜒河流的曲率。当局部河段的曲率小于截断距离时,河流在该点处变直。
为了模拟河道的立体特征,使用简化的U形和V形河道来近似河道截面(图3)。U形河道通常位于平缓的地形中,主要由侧向侵蚀形成。V形河道通常出现在坡度陡峭的地区,主要由垂直侵蚀形成[25]。
U形河道可以采用抛物线函数近似:
$ U(x) = \left\{ {\begin{array}{*{20}{l}}{4{D_c}{{\left( {x/{W_c}} \right)}^2} - {D_c},}&{x \leqslant {W_c}} \\ {0,}&{x \gt {W_c}} \end{array}} \right. $
式中:x是从中心线到网格上任何点的欧几里德距离;Dc是河道的最大深度;Wc是河道宽度。
V形河道可以采用高斯函数和抛物线函数的组合近似:
$ \begin{split}& V(x)= \\ &\left\{\begin{aligned} & \min[4D_c\left(x/W_c\right)^2-D_c,\text{ }-D_c\mathrm{e}^{-x^2/\left[2\left(W_c/4\right)^2\right]}], & x\leqslant W_c \\ &0, & x \gt W_c\end{aligned}\right.\end{split}$
简化的河道横截面能够以较低计算成本捕捉河道的主要特征。河道构建后,将其嵌入三维层状模型中,河道嵌入层状模型时每个河道的深度和方向是随机选择的,能够反映河道的纵向叠置关系。考虑实际条件下,河道和地层会由于地质运动发生弯曲变形。因此,在阻抗模型中引入了倾斜和褶皱等地质构造以增强合成地震体的多样性和真实性,此外还可以在模型中加入断层以模拟断裂构造。
通过垂直剪切模拟褶皱结构,剪切可以分解为位移场$ {S_1}(X,Y,Z) $和$ {S_2}(X,Y,Z) $,分别使得地层倾斜和弯曲[26]:
$ \left\{\begin{aligned} & S_1(X,Y,Z)=aX+bY+c_0, \\ & S_2(X,Y,Z)=\dfrac{1.5}{Z_{\max}}Z\displaystyle\sum\limits_{k=1}^{N}b_k\mathrm{e}^{\frac{\left(X-c_k\right)^2+\left(Y-d_k\right)^2}{2\sigma_k^2}},\end{aligned}\right. $
式中:a、b和c0表示倾斜结构;N为二维高斯函数的数目;(ck,dk)表示每个高斯函数的中心;σk和bk为第k个高斯函数的半宽度和幅度。通过使用剪切位移场,原始空间中的初始平层模型被映射到褶皱空间,据此可以创建具有不同褶皱结构和变形弯曲河道特征的反射率模型。在获得阻抗模型后,可以利用阻抗模型计算地震反射率,反射率模型与Ricker子波进行卷积可以获得地震数据。
数值模拟方法可生成大量三维地震数据及其河道标签,提供更多样化的训练样本,增加模型的泛化能力,提升对不同地质条件下河道特征的识别能力。图4给出了部分合成地震数据及其相应的河道标签,其中包含了多种类型的河道。合成的三维地震数据集保留了河道特征的空间信息,提供了更准确和连续的河道数据,使得深度神经网络能更有效地捕捉和学习河道的空间分布与形态,从而提高河道砂体的检测效果。
为实现对三维地震数据中河道砂体的高精度自动检测与识别,本文构建了一种基于融合注意力机制的三维U-Net结构的深度卷积神经网络(AE-Unet)[27],用于地震数据的河道检测任务,如图5所示。该网络在传统3D U-Net编码—解码架构的基础上引入了squeeze and excitation(SE)注意力机制,以增强模型对河道特征的重要性建模能力,从而提高网络的表征能力和分割性能。AE-Unet的编码器由多个由卷积和最大池化层组成的模块构成,逐步提取多尺度的空间特征。每个卷积模块后均插入了一个SE模块,通过全局平均池化压缩空间信息后,借助两个全连接层学习通道间的显著性权重,并将其与输入特征图逐通道相乘,实现显著性重加权,提升特征表达的判别性。在解码过程中,网络通过上采样,并与对称位置的编码特征图进行特征级拼接,以融合浅层的空间细节和深层的语义特征。上采样后仍使用双层卷积提取局部信息,并插入SE模块以维持注意力机制的连续性。网络最终使用一个1×1×1的卷积层将多通道特征映射压缩为单通道输出,配合sigmoid激活函数用于二分类分割。AE-Unet通过融合SE注意力模块,有效提升了三维空间特征建模能力,适用于高精度三维分割与重建任务。AE-Unet模型具有结构对称、特征融合充分、注意力机制有效等特点,尤其适用于具有高噪声、低对比度以及非规则边界的河道砂体检测任务。
在网络训练前可以对数据进行预处理,其中数据增强和归一化可以提高深度学习分类器精度及模型的泛化能力。数据增强通过对现有训练样本施加改变从而产生新的训练样本,能够在扩大数据量的同时增加训练样本的多样性,可以防止网络学习无关的特征,进而增强模型的泛化能力。本文从不同角度旋转数据体,使感兴趣的对象出现在数据体的不同区域。由于不同训练数据之间、训练数据和实际地震数据之间存在差异,显著影响了网络的泛化能力。因而在构建神经网络模型时,需要对参与训练的合成地震数据和用于预测的野外地震数据进行归一化预处理。数据归一化能够让不同数据的特征满足相似的数值分布,提高分类精度和网络模型的泛化能力。
本文采取减去其平均值并除以其标准差的方式对地震数据进行归一化:
$ d_{\mathrm{std}}=\frac{d-\mu}{\sigma}\ , $
式中:dstd为标准化后的地震数据;d表示输入地震数据;μ和σ分别表示地震数据的平均值和标准差。
数据集中包含河道数据和背景数据,由于背景数据的数量远多于河道数据,因此数据集会存在不平衡现象。为了解决训练样本分布不平衡的问题,本文使用平衡交叉熵损失函数作为深度学习网络的损失函数:
$ L=-\beta\sum\limits_{i=0}^{N}y_i\mathrm{lg}(p_i)-(1-\beta)\sum\limits_{i=0}^{N}(1-y_i)\mathrm{lg}(1-p_i)\ , $
式中:$ \beta = \displaystyle\sum\limits_{i = 0}^{N} {(1 - {y_i})} /N $,表示非河道样本点与总样本点的比值,即非河道样本点所占的比例;1−β表示三维地震数据中河道样本点所占的比例。第一项表明非河道样本点所占比例β越高,河道样本点处的预测误差所占权重也越高;第二项表明河道样本点所占比例1−β越低,非河道点处的预测误差所占权重也就越低。因此,β系数的引入能够改善河道砂样本和非河道样本之间的不平衡问题。
采用keras作为框架构建河道检测网络模型,模型的输入大小为128×128×128的三维数据体,其中训练数据200组,验证数据20组,优化器采用了Adam,学习率为0.0001,损失函数为平衡交叉熵损失函数。训练了30个轮次,每训练完1个轮次,都使用验证集进行验证。为了获得性能良好的神经网络,网络模型的训练轮次的设置十分重要。如果训练轮次太少,被训练的网络会因为对数据的学习过程不够充分而造成欠拟合的现象;当训练轮次太多时,网络会对数据中存在的噪声也进行拟合,进而造成网络模型过拟合的现象。训练结果如图6所示,训练过程中训练准确度稳定上升,训练误差则稳定下降,验证准确度与验证误差也与训练过程的变化保持一致,模型训练良好,并未出现明显的过拟合或欠拟合现象。
对于二分类问题而言,模型需要判断数据中每个样本点的预测结果是河道还是非河道,也可以说是1还是0(或者说是positive 还是negative)。在已知样本点真实值的情况下,根据样本点预测值是否正确统计数据,得到四个基础指标:真正例(true positive,TP)、真负例(true negative,TN)、假正例(false positive,FP)、假负例(false negative,FN)。
准确率(accuracy)为所有样本点中模型预测正确的样本点所占比例:
$ accuracy=\frac{TP+TN}{TP+TN+FP+FN}\ 。 $
在样本分布不平衡的情况下,准确率指标并不能很好地说明网络模型的性能。为了更好地评价网络模型的河道检测性能,计算了分类模型的两种量化评判指标,分别是受试者工作特征曲线(receiver operating characteristic curve,ROC)和精确率—召回率曲线(precision-recall,PR)。
在ROC 曲线图中,横坐标代表的是假正例率(false positive rate,FPR),纵坐标代表的是真正例率(true positive rate,TPR)。在真实值为河道的所有样本点中,模型预测为河道的样本点所占比例为真正例率;在真实值为非河道的所有样本点中,模型预测错误为河道的样本点所占比例为假正例率:
$ \mathit{\mathit{{TPR}}}=\frac{TP}{TP+FN}\text{,}\mathit{{FPR}}=\frac{FP}{TN+FP}。 $
精确率是在模型预测值是河道砂的所有样本点中,预测正确的样本点所占的比重;召回率和真正例率定义相同:
$ \mathit{precision}=\frac{TP}{TP+FP}\text{,}\mathit{{recall = TPR}}=\frac{TP}{TP+FN}\ 。 $
如图7所示,给出了受试者工作特征曲线(ROC)以及精确率—召回率曲线(PR)。对应于 ROC 曲线左上角(FPR与TPR)的数据点被认为是一个好的模型,而位于曲线对角线部分的数据点则不被认为是一个好的模型。
基于深度学习的河道自动识别提供了一种端到端的一体化解决方案,简化了传统的河道解释流程,提高了工作效率和准确性。深度神经网络在大量的人工合成数据上进行训练,能够自主学习有效的河道特征,并具备强大的非线性拟合和特征提取能力。考虑到野外地震数据的数据量较大和内存限制,对实际数据进行测试时,需要将实际数据划分为较小的块并分别进行预测。由于原始数据被分成了多个块进行预测,预测结果也是对应的块级别的河道预测。因此,需要将预测结果进行拼接,以获得完整的三维河道预测。为了避免拼接效应(对将小块恢复为原始数据的影响)和边界效应(对边界预测的影响),需要采用重叠的分块策略,在分块时让相邻块有一定的重叠区域,以保证河道砂在重叠区域上的连续性。本文采用连续有重叠的分块方式来减弱小块体之间的拼接痕迹。重叠宽度的大小也会影响整个地震数据体的预测时间和效果,重叠部分越多,切割出的小块体就会越多,需要进行预测的时间也就越长。
为了检验网络模型的训练效果,使用与训练数据尺寸相同的人工合成地震数据对网络进行测试,如图8所示,对于未包含在训练数据集中的合成地震体,使用训练的深度学习网络进行河道检测。由图8可知,检测到的河道与标签数据中河道的真实值能够较好地匹配。网络经过训练之后,可以有效地学习到地震数据中的河道特征,能够准确预测出测试数据中河道位置。网络是直接对含噪地震数据进行河道检测的,说明它还具有一定的抗噪能力。训练完备的网络能够较为准确地检测出地震数据的大部分河道,具有一定的泛化性和实用性,可以实现高效和自动化河道检测,结合图6a可知,准确率可达90%以上。
准中 4 区块头屯河组砂体厚度与规模明显较小,曲流河沉积主要分布在中部 4 区块的头屯河组三段(J2t3)。图9a为地震数据,图9b为计算获得的均方根振幅(root mean square amplitude,RMS)属性,均方根振幅有助于区分声阻抗变化区域,这些变化可能归因于岩性变化;图9c为计算获得的相干体属性,相干性属性能够帮助识别和可视化具有显著横向不连续性的地质特征(如断层、裂缝)以及地层特征(如河道边缘);图9d为准中地区的三维地震数据河道识别结果。由图可知,采用本文方法能够有效地识别河道。综合属性以及深度学习河道概率预测的结果,能够分析该工区的河道特征。
图10显示了该工区J2t31层位河道砂体概率,D18井位于主河道拐弯处,在J2t31层位有较厚的砂体,D21井所在J2t31层位位置河道砂体较薄,而D101井所在J2t31层位位置未钻遇河道砂体。砂体概率预测结果与实际钻井结果吻合,验证了本文方法的有效性。
通过使用合成地震数据集对卷积网络进行训练,网络在训练中利用地震数据进行学习,最终将学习得到的网络模型应用于实际地震数据中,河道在地震数据体中得到了很好的解释。模拟的河道形态在地质上是合理的,使网络能够实现准确的河道识别。由于建模过程是以相对阻抗的形式将各种类型的河道添加到合成模型中,因此,使用合成训练数据集训练的网络可以适应不同沉积环境下形成的不同岩性河道的识别;由于工作流程中模拟的多种类型的河道数量是随机设定的,并且河道的方向、宽度、厚度和相对阻抗值随空间位置而变化,因此,使用合成训练数据集训练的网络可以适应复杂河道的识别。
河流相沉积孔隙度和渗透率较高,对研究储层特征、评估油气勘探潜力至关重要。传统的河流相识别方法往往依赖于地震属性,需要人工提取河道特征,尤其是在解释三维地震数据时,效率低下。本文研究了一种基于深度学习的地震数据河道检测方法,得到的结论如下:
1)将深度学习网络应用于河道解释的主要限制是缺乏训练数据集。本文通过数值模拟生成合成地震数据及其河道标签,使用三维合成地震数据和河道砂体标签来训练神经网络,训练完成后,神经网络能够准确地检测三维地震数据中的河道。
2)训练完备的深度学习网络能够较为准确地检测出实际地震数据的大部分河道,且具有较好的泛化性和实用性,可以实现高效和自动化河道检测。
当然,由于野外数据的复杂性和多样性,合成记录和野外地震数据集之间仍存在差距,对合成地震数据的进一步改进可以使预测更加稳健,此外还可以考虑在河道解释中应用迁移学习,以减少训练和现场地震数据之间的差异。

参考文献 引证文献
排序方式:
1
邓琳平, 丁峰, 林龙波, 等. 河流相砂体边界预测方法研究[J]. 海洋地质前沿, 2022, 38(3): 59−64.
Deng L P, Ding F, Lin L B, et al. A review of prediction methods for fluvial sand boundary[J]. Marine Geology Frontiers, 2022, 38(3): 59−64.
2
徐世东, 陈书平, 薛佳雯, 等. 井震数据联合驱动下砂体叠置模式构建技术及应用——以WX油田东北部姚家组葡萄花油层为例[J]. 石油地球物理勘探, 2023, 58(1): 178−189.
Xu S D, Chen S P, Xue J W, et al. Construction technology of superimposition patterns of sandbodies driven by well-seismic data and its application: Taking the Putaohua reservoir of Yaojia Formation in the northeastern WX Oilfield as an example[J]. Oil Geophysical Prospecting, 2023, 58(1): 178−189.
3
张运龙, 丁峰, 尹成, 等. 基于地震波形结构属性识别河流相砂体叠置区[J]. 石油学报, 2018, 39(7): 792−801.
Zhang Y L, Ding F, Yin C, et al. The identification of fluvial sand-body superimposed area based on seismic waveform structure attributes[J]. Acta Petrolei Sinica, 2018, 39(7): 792−801.
4
任宪军, 李钟, 马应龙, 等. 地震分频迭代反演在薄层河道砂体预测中的应用[J]. 物探与化探, 2023, 47(2): 420−428.
Ren X J, Li Z, Ma Y L, et al. Application of seismic frequency-divided iterative inversion in the prediction of thinly laminated channel sand bodies[J]. Geophysical and Geochemical Exploration, 2023, 47(2): 420−428.
5
Marfurt K J, Sudhaker V, Gersztenkorn A, et al. Coherency calculations in the presence of structural dip[J]. Geophysics, 1999, 64(1): 104−111.
6
Marfurt K J, Kirlin R L, Farmer S L, et al. 3-D seismic attributes using a semblance-based coherency algorithm[J]. Geophysics, 1998, 63(4): 1150−1165.
7
Hart B S. Channel detection in 3-D seismic data using sweetness[J]. AAPG Bulletin, 2008, 92(6): 733−742.
8
Wu X M. Directional structure-tensor-based coherence to detect seismic faults and channels[J]. Geophysics, 2017, 82(2): A13−A17.
9
何小龙, 张兵, 杨凯, 等. 基于沉积微相特征挖掘的随机森林岩石相测井识别方法——以新场地区须家河组二段致密砂岩为例[J]. 物探与化探, 2024, 48(5): 1337−1347.
He X L, Zhang B, Yang K, et al. A log-based lithofacies identification method based on random forest and sedimentary microfacies characteristics: A case study of tight sandstones in the second member of the Xujiahe Formation in the Xinchang area[J]. Geophysical and Geochemical Exploration, 2024, 48(5): 1337−1347.
10
Ren S, He K, Girshick R, et al. Faster R-CNN: Towards realtime object detection with region proposal networks[J]. Advances in Neural Information Processing Systems, 2015: 91-99.
11
唐杰, 韩盛元, 刘英昌, 等. 基于去噪卷积神经网络的面波噪声压制方法[J]. 石油物探, 2022, 61(2): 245−252.
Tang J, Han S Y, Liu Y C, et al. Seismic surface wave attenuation based on denoising convolutional neural networks[J]. Geophysical Prospecting for Petroleum, 2022, 61(2): 245−252.
12
Chen L C, Zhu Y K, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Computer Vision – ECCV 2018. Cham: Springer, 2018: 833-851.
13
Zhang Y Y, Lu P, Yu H, et al. Enhancement of seismic imaging: An innovative deep learning approach[EB/OL]. 2019: arXiv: 1909.06016. https://arxiv.org/abs/1909.06016.
14
Di H B, AlRegib G. A comparison of seismic saltbody interpretation via neural networks at sample and pattern levels[J]. Geophysical Prospecting, 2020, 68(2): 521−535.
15
唐杰, 孟涛, 韩盛元, 等. 基于多分辨率U-Net网络的地震数据断层检测方法[J]. 石油地球物理勘探, 2021, 56(3): 436−445, 409.
Tang J, Meng T, Han S Y, et al. A fault detection method of seismic data based on MultiResU-Net[J]. Oil Geophysical Prospecting, 2021, 56(3): 436−445, 409.
16
Zhang H, Song X H, Zhu P M, et al. A two-stage convolutional neural network for interactive channel segmentation from 3-D seismic data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5915915.
17
Pham N, Fomel S, Dunlap D. Automatic channel detection using deep learning[J]. Interpretation, 2019, 7(3): SE43−SE50.
18
Gramstad O, Goledowski B, Nickel M. Automated channel detection using deep convolutional neural networks[C]//San Antonio: SEG Technical Program Expanded Abstracts 2019, Society of Exploration Geophysicists, 2019: 2483-2487.
19
Wu X M, Liang L M, Shi Y Z, et al. FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation[J]. Geophysics, 2019, 84(3): IM35−IM45.
20
Gao H, Wu X M, Liu G F. ChannelSeg3D: Channel simulation and deep learning for channel interpretation in 3D seismic images[J]. Geophysics, 2021, 86(4): IM73−IM83.
21
Wang G Y, Wu X M, Zhang W. cigChannel: A large-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation[J]. Earth System Science Data, 2025, 17(7): 3447−3471.
22
Zhang X K, Lou Y H, Liu N H, et al. 3-D UXSE-net for seismic channel detection based on satellite image enhanced synthetic datasets[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18: 8300−8311.
23
Nanson G C, Hickin E J. Channel migration and incision on the beatton river[J]. Journal of Hydraulic Engineering, 1983, 109(3): 327−337.
24
Howard A D, Knutson T R. Sufficient conditions for river meandering: A simulation approach[J]. Water Resources Research, 1984, 20(11): 1659−1667.
25
Sylvester Z, Durkin P, Covault J A. High curvatures drive river meandering[J]. Geology, 2019, 47(3): 263−266.
26
Wu X M, Geng Z C, Shi Y Z, et al. Building realistic structure models to train convolutional neural networks for seismic structural interpretation[J]. Geophysics, 2020, 85(4): WA27−WA39.
27
Li H Z, Ren Z H, Zhu G Q, et al. AE-UNet: A composite lung CT image segmentation framework using attention mechanism and edge detection[J]. The Journal of Supercomputing, 2024, 81(1): 331.
2026年第50卷第1期
84
41
0
引用本文
BibTeX
文章信息
doi: 10.11720/wtyht.2026.1283
  • 接收时间:2025-08-25
  • 首发时间:2026-11-12
  • 出版时间:2026-02-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-08-25
  • 修回日期:2025-11-14
基金
作者信息
    中国石油化工股份有限公司 胜利油田分公司勘探开发研究院,山东 东营 257015
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/wtyht/CN/10.11720/wtyht.2026.1283
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