Article(id=1328032087535366847, tenantId=1146029695717560320, journalId=1311385891987619962, issueId=1328031851136004804, articleNumber=null, orderNo=null, doi=10.12090/j.issn.1006-6616.2025108, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1754582400000, receivedDateStr=2025-08-08, revisedDate=1768320000000, revisedDateStr=2026-01-14, acceptedDate=1768492800000, acceptedDateStr=2026-01-16, onlineDate=1794557123310, onlineDateStr=2026-11-13, pubDate=1772208000000, pubDateStr=2026-02-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794557123310, onlineIssueDateStr=2026-11-13, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794557123310, creator=13701087609, updateTime=1794557123310, updator=13701087609, issue=Issue{id=1328031851136004804, tenantId=1146029695717560320, journalId=1311385891987619962, year='2026', volume='32', issue='1', pageStart='1', pageEnd='284', issueExtLink='null', onlineDate='null', pubDate='1772208000000', pubDateStr='2026-02-28', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794557066949, creator='13701087609', updateTime=1794557066949, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=245, endPage=257, ext={EN=ArticleExt(id=1328032087728304832, articleId=1328032087535366847, tenantId=1146029695717560320, journalId=1311385891987619962, language=EN, title=An intelligent lithofacies identification method for well logging of deep carbonate rocks incorporating sequence stratigraphic prior information, columnId=null, journalTitle=Journal of Geomechanics, columnName=null, runingTitle=null, highlight=null, articleAbstract=
Objective

Lithofacies identification constitutes a core component of reservoir characterization and is of great significance for oil and gas exploration and development. Traditional lithofacies identification relies primarily on expert experience and manual interpretation, suffering from high subjectivity, low efficiency, and poor consistency. Moreover, identifying carbonate lithofacies such as bioreefs and bioclastic shoals solely through geological and geophysical data combined with limited core samples and thin-section analysis is labor-intensive and cannot meet the requirements of refined oil and gas field development. This study aims to address the major challenges in intelligent lithofacies identification, namely the insufficient modeling of spatial dependencies in the depth direction, the lack of technical prior knowledge, and the inadequate integration of geological understanding with data-driven approaches.

Methods

We propose an intelligent well-logging lithofacies identification method for deep carbonate rocks that integrates sequence stratigraphic prior information. The method applies a deep neural network, termed Sequence-Constrained Long Short-Term Memory Network (SC-LSTM), as its core framework. This network embeds sequence stratigraphic units as geological constraints into the input feature space of the model, achieving an organic integration of geological understanding with logging response characteristics. The network architecture comprises two parallel feature extraction modules: a curve feature extraction module that utilizes convolutional layers to extract local patterns and depth-directional variation characteristics from logging responses, and a sequence feature extraction module that performs convolutional encoding on sequence division schemes to convert discrete sequence and system tract information into continuous feature representations. The method uses conventional well logs, including natural gamma ray, acoustic transit time, density, neutron, and resistivity as input data. A sliding time-window sampling strategy expands the training dataset to address the problem of limited labeled samples, while a weighted averaging prediction method enhances the stability and reliability of the identification results.

Results

The application to the Changxing Formation carbonate reservoir in the Yuanba gas field demonstrates that an optimal sample length of 40 meters can (i) completely cover the vertical evolution sequence from reef base to reef core to reef cap, or (ii) encompass a complete reef-shoal depositional combination controlled by sea-level cycles. This, enables the model to fully learn the orderly stacking patterns and facies transition characteristics within sequence units. The model achieved 92% identification accuracy on the test set. Comparative experiments between conventional LSTM and SC-LSTM networks reveal that the proposed method effectively avoids geologically unreasonable predictions that may arise from relying solely on logging response characteristics. For example, it avoids erroneously predicting reef cap facies during the early highstand system tract or misidentifying reef cap facies as reef/shoal interfacies at reef tops.

Conclusions

These findings confirm that the integration of sequence stratigraphic prior information can effectively constrain model predictions and avoid geologically unreasonable results. The conventional LSTM model learns lithofacies characteristics only from numerical patterns of logging curves and easily confuses lithofacies types with similar logging responses under different sequence backgrounds. In contrast, the SC-LSTM model enables the network to understand the geological rules and the combined characteristics of lithofacies development within different sequence units and system tracts by fusing sequence stratigraphic information. This improves the geological rationality and prediction accuracy of lithofacies identification. [Significance] The significance of this study lies not only in its practical applications—enabling rapid establishment of regional lithofacies distribution patterns to guide well deployment and providing timely support for reservoir fine characterization and the exploitation of remaining oil and gas potential through the real-time updating of lithofacies interpretation schemes as new well data accumulate—but also in its theoretical contributions. It particularly advances the integration of domain knowledge with artificial intelligence technology by linking sequence stratigraphy theory, depositional environment evolution, and deep learning algorithms in a unified framework for intelligent lithofacies identification. This opens new avenues for automated and intelligent reservoir characterization in complex carbonate formations.

, authors=Mingdi ZHANG1, Meng LI2, *, Yuanyang LIU1, Yuan HUANG2, Shuyue CUI2, authorsList=Mingdi ZHANG, Meng LI, Yuanyang LIU, Yuan HUANG, Shuyue CUI, authorCompany=null, correspAuthors=Meng LI, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright ©2026 Journal of Geomechanics. 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=1328032089498301137, articleId=1328032087535366847, tenantId=1146029695717560320, journalId=1311385891987619962, language=CN, title=融合层序地层先验信息的测井岩相智能识别方法, columnId=null, journalTitle=地质力学学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

岩相识别是储层表征的核心环节,对油气勘探开发具有重要意义。传统岩相识别主要依赖专家经验和人工解释,存在主观性强、效率低、一致性差等问题。文章针对碳酸盐岩生物礁、生屑滩等复杂岩相识别工作量大、精度低的难题,提出了一种层序地层先验约束下的深层碳酸盐岩测井岩相智能识别方法。该方法创新性地将层序地层学理论与深度学习技术深度融合,通过双分支神经网络架构分别提取测井响应特征和层序地层约束信息,并在特征空间实现有机融合,使模型在学习测井曲线数值模式的同时,遵循层序格架内岩相空间配置规律和垂向演化序列,有效解决了纯数据驱动方法易产生地质不合理预测的问题。方法采用自然伽马、声波时差、密度、电阻率等常规测井曲线及层序划分方案作为输入,利用卷积神经网络提取多尺度特征,通过长短时记忆模块(LSTM)实现岩相纵向演化的时序依赖关系建模。针对碳酸盐岩礁滩体发育规模,优选40 m样本长度以完整覆盖礁基−礁核−礁盖垂向序列或海平面旋回控制的沉积组合,并采用滑动时窗加权平均预测策略提升结果稳定性。元坝气田长兴组测井岩相识别应用表明,相比常规LSTM方法,新方法识别结果符合礁体演化规律,单井预测时间仅需5~10秒,效率较人工解释提升2~3个数量级,实现了岩相识别的自动化、智能化和地质合理化。

, authors=张明迪1, 李蒙2, *, 刘远洋1, 黄渊2, 崔书岳2, authorsList=张明迪, 李蒙, 刘远洋, 黄渊, 崔书岳, authorCompany=null, correspAuthors=李蒙, authorNote=

张明迪(1982—),男,硕士,副研究员,主要从事川东北地区油气藏工程、流体相态、油气藏渗流、高含硫油气开发等方面研究。Email:

, correspAuthorsNote=
李蒙(1988—),男,博士,副研究员,主要从事地球物理和人工智能交叉学科研究。Email:
, copyrightStatement=版权所有©《地质力学学报》编辑部 2026, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=7qC+rXp8pjAC3CyjY5/hbQ==, magXml=/aZ+JaYbLBRzy3ukXT3W/A==, pdfUrl=null, pdf=D5+182YQ5ROp3YgDsWQKOw==, pdfFileSize=7721771, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=vg5HhEqZ8sisTr0EpzR5hA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=F1SExp+0M7DlrqRy+Tloow==, mapNumber=null, fund=null)}, authors=[Author(id=1328032090005811929, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangmingdi.xnyq@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032091717087963, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032090005811929, language=EN, stringName=Mingdi ZHANG, firstName=Mingdi, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032091796779740, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032090005811929, language=CN, stringName=张明迪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国石油化工股份有限公司西南油气分公司,成都 610041, bio={"content":"

张明迪(1982—),男,硕士,副研究员,主要从事川东北地区油气藏工程、流体相态、油气藏渗流、高含硫油气开发等方面研究。Email:

"}, bioImg=null, bioContent=

张明迪(1982—),男,硕士,副研究员,主要从事川东北地区油气藏工程、流体相态、油气藏渗流、高含硫油气开发等方面研究。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089779319506, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=1, ext=[AuthorCompanyExt(id=1328032089787708115, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China), AuthorCompanyExt(id=1328032089800291028, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国石油化工股份有限公司西南油气分公司,成都 610041)])]), Author(id=1328032091868082910, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=limeng.syky@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1328032091947774688, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032091868082910, language=EN, stringName=Meng LI, firstName=Meng, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092052632289, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032091868082910, language=CN, stringName=李蒙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089892565717, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=2, ext=[AuthorCompanyExt(id=1328032089913537238, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China), AuthorCompanyExt(id=1328032089921925847, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206)])]), Author(id=1328032092123935459, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=182518415@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032092216210149, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092123935459, language=EN, stringName=Yuanyang LIU, firstName=Yuanyang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092308484838, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092123935459, language=CN, stringName=刘远洋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国石油化工股份有限公司西南油气分公司,成都 610041, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089779319506, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=1, ext=[AuthorCompanyExt(id=1328032089787708115, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China), AuthorCompanyExt(id=1328032089800291028, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国石油化工股份有限公司西南油气分公司,成都 610041)])]), Author(id=1328032092400759528, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=huangyuan.syky@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032092480451306, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092400759528, language=EN, stringName=Yuan HUANG, firstName=Yuan, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092560143083, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092400759528, language=CN, stringName=黄渊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089892565717, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=2, ext=[AuthorCompanyExt(id=1328032089913537238, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China), AuthorCompanyExt(id=1328032089921925847, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206)])]), Author(id=1328032092669194989, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cuisy.syky@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032092761469679, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092669194989, language=EN, stringName=Shuyue CUI, firstName=Shuyue, middleName=null, lastName=CUI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092836967152, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092669194989, language=CN, stringName=崔书岳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089892565717, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=2, ext=[AuthorCompanyExt(id=1328032089913537238, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China), AuthorCompanyExt(id=1328032089921925847, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206)])])], keywords=[Keyword(id=1328032092946019057, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, orderNo=1, keyword=well logging lithofacies identification), Keyword(id=1328032093029905138, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, orderNo=2, keyword=intelligent identification), Keyword(id=1328032093126374131, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, orderNo=3, keyword=sequence stratigraphic prior information), Keyword(id=1328032093227037428, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, orderNo=4, keyword=deep learning), Keyword(id=1328032093315117813, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, orderNo=5, keyword=carbonate reservoir; SC-LSTM), Keyword(id=1328032093403198198, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, orderNo=1, keyword=测井岩相识别), Keyword(id=1328032093491278583, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, orderNo=2, keyword=智能), Keyword(id=1328032093579358968, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, orderNo=3, keyword=层序地层先验), Keyword(id=1328032093680022265, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, orderNo=4, keyword=识别效率), Keyword(id=1328032093772296954, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, orderNo=5, keyword=识别精度)], refs=[Reference(id=1328032097463284495, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, 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=ABUZEID A M, BAGHDADY A R, KASSEM A A, 2025. Automated lithofacies classification: a comprehensive machine learning approach in Shushan Basin reservoirs, Western Desert, Egypt[J]. Journal of African Earth Sciences, 223: 105487., articleTitle=null, refAbstract=null), Reference(id=1328032097538781968, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=AL-MUDHAFAR W J, 2020. Integrating machine learning and data analytics for geostatistical characterization of clastic reservoirs[J]. Journal of Petroleum Science and Engineering, 195: 107837., articleTitle=null, refAbstract=null), Reference(id=1328032097643639569, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=ANTARIKSA G, MUAMMAR R, LEE J, 2022. Performance evaluation of machine learning-based classification with rock-physics analysis of geological lithofacies in Tarakan Basin, Indonesia[J]. Journal of Petroleum Science and Engineering, 208: 109250., articleTitle=null, refAbstract=null), Reference(id=1328032097735914258, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=BHATTACHARYA S, MISHRA S, 2018. Applications of machine learning for facies and fracture prediction using Bayesian Network Theory and Random Forest: case studies from the Appalachian basin, USA[J]. Journal of Petroleum Science and Engineering, 170: 1005-1017., articleTitle=null, refAbstract=null), Reference(id=1328032097815606035, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=CAO J X, CHEN S Y, XIAO B Y, et al., 2025. Machine learning based diagenetic facies logging identification: a case of Shaximiao Formation in central Sichuan Basin[J]. Science Technology and Engineering, 25(21): 8858-8870. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032097899492116, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN C, WANG L, ZHAO W Y, et al., 2024. Seismic facies and sedimentary distribution characteristics of the Upper Carboniferous in the Ounan Depression, eastern Qaidam Basin[J]. Journal of Geomechanics, 30(3): 408-418. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032097974989589, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN K, WANG Y L, LU Y X, et al., 2025. Sedimentary characteristics of the Lower Cambrian Shuijingtuo Formation in the E’Xi trough and its petroleum geological significance[J]. Journal of Geomechanics, 31(4): 604-616. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032098046292758, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN X J, FENG Z T, ZENG F R, et al., 2024. Development status of logging-based lithology identification technology for shale formations[J]. Xinjiang Petroleum Geology, 45(6): 742-752. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032098117595927, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=DATTA D, SINGH G, SINGH S K, et al., 2023. Application of multivariate change detection in automated lithofacies classification from well-log data in a nonstationary subsurface[J]. Journal of Applied Geophysics, 215: 105094., articleTitle=null, refAbstract=null), Reference(id=1328032098188899096, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=DONG S Q, ZENG L B, JI C Q, et al., 2024. A deep kernel method for fracture identification in ultra-deep tight sandstones using well logs[J]. Earth Science Frontiers, 31(5): 166-176. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032098289562393, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=GAO F, QU Z P, WEI Z, et al., 2024. Study on well-log lithofacies classification based on machine learning methods[J]. Progress in Geophysics, 39(3): 1173-1192. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032098369254170, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=GAO Y N, TIAN M, GRANA D, et al., 2025. Attention mechanism‐assisted recurrent neural network for well log lithology classification[J]. Geophysical Prospecting, 73(2): 628-649., articleTitle=null, refAbstract=null), Reference(id=1328032098440557339, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=HAN W L, WANG Y B, GAO X D, et al., 2016. Identification of sedimentary microfacies based on BP neural network[J]. Coal Technology, 35(12): 114-116. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032098557997852, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=HE X H, LI K S, XU J C, et al., 2023. Application of log lithofacies classification model based on clustering-support vector classification method[J]. Well Logging Technology, 47(2): 129-137. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032098633495325, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=HOU X M, LIAN P Q, ZHAO J Y, et al., 2024. Identification of carbonate sedimentary facies from well logs with machine learning[J]. Petroleum Research, 9(2): 165-175., articleTitle=null, refAbstract=null), Reference(id=1328032098713187102, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=HUANG Q L, ZHAO J L, BAI Q, et al., 2024. Automatic recognition of sedimentary microfacies based on Adaboost algorithm: taking the Shanxi Formation in Q zone of Longdong gas field as an example[J]. Geological Bulletin of China, 43(4): 658-666., articleTitle=null, refAbstract=null), Reference(id=1328032098797073183, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=IPPOLITO M, FERGUSON J, JENSON F, 2021. Improving facies prediction by combining supervised and unsupervised learning methods[J]. Journal of Petroleum Science and Engineering, 200: 108300., articleTitle=null, refAbstract=null), Reference(id=1328032098893542176, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=LAI J, SONG X Y, YANG X, et al., 2025. Research progresses of comprehensive well logging evaluation methods of tight gas sandstone reservoirs[J]. Acta Petrolei Sinica, 46(1): 220-235. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032098973233953, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=LI C, JIA J, SHEN A J, et al., 2020. New method for quantitative identification of carbonate lithofacies based on conventional logging curves and its application[J]. Progress in Geophysics, 35(5): 1792-1802. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032100659344162, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=LI C, SHEN A J, CHANG S Y, et al., 2021. Application and contrast of machine learning in carbonate lithofacies log identification: a case study of Longwangmiao Formation of MX area in Sichuan Basin[J]. Petroleum Reservoir Evaluation and Development, 11(4): 586-596. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032100743230243, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=LI N, NING B S, WU H L, et al., 2021. Application status and prospects of artificial intelligence in well logging and formation evaluation[J]. Acta Petrolei Sinica, 42(4): 508-522. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032100814533412, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Y J, LAI F Q, XU H, et al., 2025. Intelligent identification methods for shale lithology based on the coupling deeply of logging curves[J]. Bulletin of Geological Science and Technology, 44(1): 308-320. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032100898419493, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=LU J, LIU M, WANG X C, 2024. Log identification method of sedimentary microfacies in deep carbonate rocks by decision tree[J]. Well Logging Technology, 48(2): 179-189. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032100990694182, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=MENG Y, JAI G H, LI C H, et al., 2025. Logging identification and application of diagenetic facies of clastic reservoir by unsupervised learning technology: a case study of the Santai Formation in Zhanhua sag, Bohai Bay Basin[J]. Journal of Palaeogeography (Chinese Edition), 27(3): 746-762. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101061997351, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=QI C S, DING L, JIAO X Y, et al., 2023. Automatic identification method of sedimentary microfacies based on bi-directional long short-term recurrent neural network: taking Dongfang B gas field in Yinggehai Basin as an example[J]. Science Technology and Industry, 23(5): 217-221. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101129106216, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=RATHORE P W S, HUSSAIN M, MALIK M B, et al., 2023. Well log analysis and comparison of supervised machine learning algorithms for lithofacies identification in Pab Formation, Lower Indus Basin[J]. Journal of Applied Geophysics, 219: 105199., articleTitle=null, refAbstract=null), Reference(id=1328032101225575209, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=SHEN L, WANG C Z, NING C Q, et al., 2023. Well-log lithofacies classification based on machine learning for Chang-7 member in Longdong area of Ordos Basin[J]. Petroleum Reservoir Evaluation and Development, 13(4): 525-536. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101322044202, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=TIAN M, LI B T, XU H M, et al., 2021a. Deep learning assisted well log inversion for fracture identification[J]. Geophysical Prospecting, 69(2): 419-433., articleTitle=null, refAbstract=null), Reference(id=1328032101405930283, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=TIAN M, OMRE H, XU H M, 2021b. Inversion of well logs into lithology classes accounting for spatial dependencies by using hidden Markov models and recurrent neural networks[J]. Journal of Petroleum Science and Engineering, 196: 107598., articleTitle=null, refAbstract=null), Reference(id=1328032101510787884, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG L Y, LIU H Q, CHENG C, et al., 2025. Research progress on intelligent identification methods for well logging lithofacies based on deep learning[J]. Progress in Geophysics, 40(4): 1773-1787. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101590479661, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG M, YANG J L, WANG X, et al., 2023. Identification of shale lithofacies by well logs based on random forest algorithm[J]. Earth Science, 48(1): 130-142. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101661782830, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=YAN J F, LI S L, WEI Z D, et al., 2025. Shale lithofacies prediction method with well-logging data based on XGBoost algorithm[J]. Journal of Palaeogeography (Chinese Edition), 27(3): 763-776. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101754057519, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG G Y, LIN C Y, WANG Z Y, et al., 2024. Hybrid knowledge-driven and data-driven intelligent reservoir characterization and its research progress[J]. Progress in Geophysics, 39(1): 119-140. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101833749296, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG H Y, XIE B, YUAN Q, et al., 2020. Logging-based sedimentary microfacies identification of Changxing Formation, Damaoping structure, Sichuan Basin[J]. Natural Gas Exploration and Development, 43(2): 38-44. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101909246769, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG T, LI Y P, LI Z K, et al, 2025. Fractures identification of deep tight reservoir with well logging based on improved long short-term memory neural network[J]. Earth Science Frontiers, 32(5): 456-465. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032101984744242, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Y J, LI Q, CAI Y D, et al., 2025. Evaluation of coal macrolithotypes based on machine learning logging inversion: a case study of the No. 8 coal seam in the Benxi Formation, Jiaxian Block, Ordos Basin[J]. Geoscience, 39(5): 1427-1436. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032102060241715, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHAO C J, JIANG Y L, WANG L J, 2022. Data-driven diagenetic facies classification and well-logging identification based on machine learning methods: a case study on Xujiahe tight sandstone in Sichuan Basin[J]. Journal of Petroleum Science and Engineering, 217: 110798., articleTitle=null, refAbstract=null), Reference(id=1328032102165099316, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHAO T P, 2025. Logging lithofacies identification of tight sandstone reservoir based on ensemble learning algorithm[J]. Offshore Oil, 45(2): 55-61. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032102236402485, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHAO Z J, LIU Y, WANG F Q, et al., 2016. Classification of borehole braided river sedimentary microfacies based on support vector machine[J]. Well Logging Technology, 40(5): 637-642. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1328032102320288566, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHENG D Y, HOU M C, CHEN A Q, et al., 2022. Application of machine learning in the identification of fluvial-lacustrine lithofacies from well logs: a case study from Sichuan Basin, China[J]. Journal of Petroleum Science and Engineering, 215: 110610., articleTitle=null, refAbstract=null), Reference(id=1328032102387397431, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=曹脊翔, 陈思源, 肖柏夷, 等, 2025. 基于机器学习的致密砂岩储层成岩相测井识别: 以川中地区沙溪庙组一段为例[J]. 科学技术与工程, 25(21): 8858-8870., articleTitle=null, refAbstract=null), Reference(id=1328032102496449336, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=陈程, 王利, 赵为永, 等, 2024. 柴东地区欧南凹陷上石炭统地震相及沉积展布特征[J]. 地质力学学报, 30(3): 408-418., articleTitle=null, refAbstract=null), Reference(id=1328032102588724025, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=陈科, 王昱荦, 卢妍欣, 等, 2025. 鄂西海槽下寒武统水井沱组沉积特征及其油气地质意义[J]. 地质力学学报, 31(4): 604-616., articleTitle=null, refAbstract=null), Reference(id=1328032102668415802, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=陈秀娟, 冯镇涛, 曾芙蓉, 等, 2024. 页岩地层测井岩性识别技术发展现状[J]. 新疆石油地质, 45(6): 742-752., articleTitle=null, refAbstract=null), Reference(id=1328032102739718971, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=董少群, 曾联波, 冀春秋, 等, 2024. 超深层致密砂岩裂缝测井识别深度核方法[J]. 地学前缘, 31(5): 166-176., articleTitle=null, refAbstract=null), Reference(id=1328032102819410748, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=高飞, 曲志鹏, 魏震, 等, 2024. 基于机器学习方法的测井岩相分类研究[J]. 地球物理学进展, 39(3): 1173-1192., articleTitle=null, refAbstract=null), Reference(id=1328032102903296829, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=韩文龙, 王延斌, 高向东, 等, 2016. 基于BP神经网络的沉积微相识别[J]. 煤炭技术, 35(12): 114-116., articleTitle=null, refAbstract=null), Reference(id=1328032102974599998, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=何贤宏, 李可赛, 许家铖, 等, 2023. 基于聚类-支持向量机算法的碳酸盐岩测井岩相识别模型与应用[J]. 测井技术, 47(2): 129-137., articleTitle=null, refAbstract=null), Reference(id=1328032103058486079, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=黄千玲, 赵军龙, 白倩, 等, 2024. 基于Adaboost算法的沉积微相自动识别: 以陇东气田Q区山西组为例[J]. 地质通报, 43(4): 658-666., articleTitle=null, refAbstract=null), Reference(id=1328032103142372160, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=赖锦, 宋翔羽, 杨薰, 等, 2025. 致密砂岩气储层测井综合评价技术研究进展[J]. 石油学报, 46(1): 220-235., articleTitle=null, refAbstract=null), Reference(id=1328032103217869633, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=李昌, 贾俊, 沈安江, 等, 2020. 基于常规测井识别微生物碳酸盐岩岩相新方法及应用[J]. 地球物理学进展, 35(5): 1792-1802., articleTitle=null, refAbstract=null), Reference(id=1328032103284978498, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=李昌, 沈安江, 常少英, 等, 2021. 机器学习法在碳酸盐岩岩相测井识别中应用及对比: 以四川盆地MX地区龙王庙组地层为例[J]. 油气藏评价与开发, 11(4): 586-596., articleTitle=null, refAbstract=null), Reference(id=1328032103373058883, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=李宁, 徐彬森, 武宏亮, 等, 2021. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 42(4): 508-522., articleTitle=null, refAbstract=null), Reference(id=1328032103461139268, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=刘粤蛟, 赖富强, 徐浩, 等, 2025. 基于测井曲线深程度耦合的页岩岩相智能识别方法[J]. 地质科技通报, 44(1): 308-320., articleTitle=null, refAbstract=null), Reference(id=1328032105151443781, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=路菁, 刘秘, 王晓畅, 2024. 深层碳酸盐岩沉积微相决策树测井识别方法[J]. 测井技术, 48(2): 179-189., articleTitle=null, refAbstract=null), Reference(id=1328032105235329862, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=孟圆, 贾光华, 李传华, 等, 2025. 基于无监督学习技术的碎屑岩储集层成岩相测井识别与应用: 以沾化凹陷三台组为例[J]. 古地理学报, 27(3): 746-762., articleTitle=null, refAbstract=null), Reference(id=1328032105323410247, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=齐春生, 丁磊, 焦祥燕, 等, 2023. 基于双向长短时循环神经网络的沉积微相自动识别方法: 以莺歌海盆地东方B气田为例[J]. 科技和产业, 23(5): 217-221., articleTitle=null, refAbstract=null), Reference(id=1328032105411490632, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=谌丽, 王才志, 宁从前, 等, 2023. 基于机器学习的鄂尔多斯盆地陇东地区长7段岩相测井识别方法[J]. 油气藏评价与开发, 13(4): 525-536., articleTitle=null, refAbstract=null), Reference(id=1328032105499571017, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=王丽媛, 刘红岐, 程超, 等, 2025. 基于深度学习的测井岩相智能识别方法研究进展[J]. 地球物理学进展, 40(4): 1773-1787., articleTitle=null, refAbstract=null), Reference(id=1328032105642177354, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=王民, 杨金路, 王鑫, 等, 2023. 基于随机森林算法的泥页岩岩相测井识别[J]. 地球科学, 48(1): 130-142., articleTitle=null, refAbstract=null), Reference(id=1328032105742840651, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=闫佳飞, 李胜利, 魏泽德, 等, 2025. 基于XGBoost算法的页岩岩相测井预测方法[J]. 古地理学报, 27(3): 763-776., articleTitle=null, refAbstract=null), Reference(id=1328032105856086860, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=张国印, 林承焰, 王志章, 等, 2024. 知识与数据融合驱动的油气藏智能表征及研究进展[J]. 地球物理学进展, 39(1): 119-140., articleTitle=null, refAbstract=null), Reference(id=1328032105931584333, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=张红英, 谢冰, 袁倩, 等, 2020. 四川盆地大猫坪构造长兴组测井沉积微相识别[J]. 天然气勘探与开发, 43(2): 38-44., articleTitle=null, refAbstract=null), Reference(id=1328032106002887502, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=张涛, 李艳萍, 李泽凯, 等, 2025. 基于改进长短记忆神经网络的深层致密储层裂缝测井识别[J]. 地学前缘, 32(5): 456-465., articleTitle=null, refAbstract=null), Reference(id=1328032106074190671, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=张云骥, 李倩, 蔡益栋, 等, 2025. 基于机器学习测井反演的宏观煤岩类型评价: 以鄂尔多斯盆地佳县区块本溪组8号煤为例[J]. 现代地质, 39(5): 1427-1436., articleTitle=null, refAbstract=null), Reference(id=1328032106162271056, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=赵天沛, 2025. 基于集成学习算法的致密砂岩储层测井岩相识别[J]. 海洋石油, 45(2): 55-61., articleTitle=null, refAbstract=null), Reference(id=1328032106246157137, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=赵忠军, 刘烨, 王凤琴, 等, 2016. 基于支持向量机的辫状河测井沉积微相识别[J]. 测井技术, 40(5): 637-642., articleTitle=null, refAbstract=null)], funds=[Fund(id=1328032097232597773, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, awardId=null, language=EN, fundingSource=This research was financially supported by the National Science and Technology Major Project (Grant No. 2025ZD1408802)., fundOrder=null, country=null), Fund(id=1328032097329066766, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, awardId=null, language=CN, fundingSource=国家科技重大专项(2025ZD1408802), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1328032089779319506, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=1, ext=[AuthorCompanyExt(id=1328032089787708115, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China), AuthorCompanyExt(id=1328032089800291028, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国石油化工股份有限公司西南油气分公司,成都 610041)]), AuthorCompany(id=1328032089892565717, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=2, ext=[AuthorCompanyExt(id=1328032089913537238, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China), AuthorCompanyExt(id=1328032089921925847, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206)])], figs=[ArticleFig(id=1328032093914903291, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 1, caption=Network structure for intelligent sedimentary microfacies identification integrating sequence stratigraphic prior information, figureFileSmall=zrvlPnKUKeDEaV6kWCL3hg==, figureFileBig=vg5HhEqZ8sisTr0EpzR5hA==, tableContent=null), ArticleFig(id=1328032093994595068, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图1, caption=融合层序地层先验信息的沉积微相智能识别网络结构, figureFileSmall=zrvlPnKUKeDEaV6kWCL3hg==, figureFileBig=vg5HhEqZ8sisTr0EpzR5hA==, tableContent=null), ArticleFig(id=1328032094233670397, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 2, caption=Principle of the sample preparation method based on sliding time window, figureFileSmall=Weu4/9rpNZ148PMFHBYcbw==, figureFileBig=NsSgXrSSplZvEsJ+WNsc8w==, tableContent=null), ArticleFig(id=1328032094317556478, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图2, caption=基于滑动时窗的样本制作方法原理, figureFileSmall=Weu4/9rpNZ148PMFHBYcbw==, figureFileBig=NsSgXrSSplZvEsJ+WNsc8w==, tableContent=null), ArticleFig(id=1328032094397248255, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 3, caption=Principle of lithofacies prediction using the weighted average method, figureFileSmall=xZoB+3okmiVrntztFmff6Q==, figureFileBig=LhfqMSXQ1oZ5NQY6v2YEeQ==, tableContent=null), ArticleFig(id=1328032094472745728, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图3, caption=加权平均法岩相预测原理, figureFileSmall=xZoB+3okmiVrntztFmff6Q==, figureFileBig=LhfqMSXQ1oZ5NQY6v2YEeQ==, tableContent=null), ArticleFig(id=1328032096163050241, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 4, caption=Planar development characteristics of the reef–shoal facies in Member 2 of the Changxing Formation in the Yuanba gas field, figureFileSmall=04C1w/w/aaL74IAPs5PsTw==, figureFileBig=XUNDxchqtd++lusEmjo66g==, tableContent=null), ArticleFig(id=1328032096267907842, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图4, caption=元坝气田长兴组二段礁滩相平面发育特征, figureFileSmall=04C1w/w/aaL74IAPs5PsTw==, figureFileBig=XUNDxchqtd++lusEmjo66g==, tableContent=null), ArticleFig(id=1328032096343405315, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 5, caption=Variation of the test set prediction accuracy with sample length, figureFileSmall=mmCGE3nQe3m0XF5aynFekQ==, figureFileBig=62YqWdCeo9bwW5m8ndU8jg==, tableContent=null), ArticleFig(id=1328032096452457220, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图5, caption=测试集预测精度随样本长度变化规律, figureFileSmall=mmCGE3nQe3m0XF5aynFekQ==, figureFileBig=62YqWdCeo9bwW5m8ndU8jg==, tableContent=null), ArticleFig(id=1328032096540537605, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 6, caption=Training process under reasonable hyperparameter combination, figureFileSmall=hd7yhYvZQjkboBjGLuSZWQ==, figureFileBig=H7dy5IkLM8aw5sU6H4picQ==, tableContent=null), ArticleFig(id=1328032096620229382, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图6, caption=合理超参数组合下的训练过程, figureFileSmall=hd7yhYvZQjkboBjGLuSZWQ==, figureFileBig=H7dy5IkLM8aw5sU6H4picQ==, tableContent=null), ArticleFig(id=1328032096699921159, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 7, caption=Comparison of lithofacies identification results between conventional LSTM and SC-LSTM networks for vertical wells, figureFileSmall=9W9h1fWQQ7KGRMGb9Fqh4Q==, figureFileBig=o1CHMb/KXKPI94V3Vk459Q==, tableContent=null), ArticleFig(id=1328032096767030024, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图7, caption=常规LSTM与SC-LSTM网络直井岩相识别推理结果对比, figureFileSmall=9W9h1fWQQ7KGRMGb9Fqh4Q==, figureFileBig=o1CHMb/KXKPI94V3Vk459Q==, tableContent=null), ArticleFig(id=1328032096842527497, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Fig. 8, caption=Comparison of lithofacies identification results between conventional LSTM and SC-LSTM networks for horizontal wells, figureFileSmall=N7u61VU5Jd0+da0FglBLaA==, figureFileBig=o5hQeYtbtMIV7oe96RiTeA==, tableContent=null), ArticleFig(id=1328032096930607882, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=图8, caption=常规LSTM与SC-LSTM网络直井岩相识别推理结果对比, figureFileSmall=N7u61VU5Jd0+da0FglBLaA==, figureFileBig=o5hQeYtbtMIV7oe96RiTeA==, tableContent=null), ArticleFig(id=1328032097001911051, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=EN, label=Table 1, caption=SC-LSTM model hyperparameter configuration, figureFileSmall=null, figureFileBig=null, tableContent=
参数类别参数名称参数值说明
样本特征参数样本长度40 m对应320个采样点(0.125 m间隔)
滑动步长5 m训练集采样步长
输入测井曲线数5条声波、自然电位、深/浅侧向、层序信息
网络结构参数卷积核大小(曲线分支)3×1捕捉局部测井响应模式
卷积核数量(曲线分支)64个第一卷积层
卷积核大小(层序分支)5×1编码层序界面突变特征
卷积核数量(层序分支)32个第一卷积层
LSTM隐藏层单元数128个记忆单元数量
LSTM层数2层堆叠LSTM层数
Dropout比率0.3防止过拟合
全连接层神经元数64个分类前的特征整合
输出类别数5种礁核、礁盖、礁基、生屑滩、礁/滩间
训练超参数批次大小(Batch Size)32个每次训练样本数
学习率(Learning Rate)0.001Adam优化器初始学习率
学习率衰减策略ReduceLROnPlateau验证损失不下降时衰减
衰减因子0.5学习率衰减倍数
耐心值(Patience)10触发衰减前的等待轮次
训练轮次(Epochs)200次最大训练轮次
早停策略启用验证损失20轮不降则停止
损失函数交叉熵损失多分类任务
优化器Adam自适应学习率优化
), ArticleFig(id=1328032097131934476, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, language=CN, label=表1, caption=

SC-LSTM模型超参数配置

, figureFileSmall=null, figureFileBig=null, tableContent=
参数类别参数名称参数值说明
样本特征参数样本长度40 m对应320个采样点(0.125 m间隔)
滑动步长5 m训练集采样步长
输入测井曲线数5条声波、自然电位、深/浅侧向、层序信息
网络结构参数卷积核大小(曲线分支)3×1捕捉局部测井响应模式
卷积核数量(曲线分支)64个第一卷积层
卷积核大小(层序分支)5×1编码层序界面突变特征
卷积核数量(层序分支)32个第一卷积层
LSTM隐藏层单元数128个记忆单元数量
LSTM层数2层堆叠LSTM层数
Dropout比率0.3防止过拟合
全连接层神经元数64个分类前的特征整合
输出类别数5种礁核、礁盖、礁基、生屑滩、礁/滩间
训练超参数批次大小(Batch Size)32个每次训练样本数
学习率(Learning Rate)0.001Adam优化器初始学习率
学习率衰减策略ReduceLROnPlateau验证损失不下降时衰减
衰减因子0.5学习率衰减倍数
耐心值(Patience)10触发衰减前的等待轮次
训练轮次(Epochs)200次最大训练轮次
早停策略启用验证损失20轮不降则停止
损失函数交叉熵损失多分类任务
优化器Adam自适应学习率优化
)], attaches=null, journal=Journal(id=1311385402311016565, delFlag=0, nameCn=地质力学学报, nameEn=Journal of Geomechanics, nameHistory1=null, nameHistory2=null, issn=1006-6616, eissn=null, cn=11-3672/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=eIT+4m2KVWPyCt/9B7VJoQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Geomechanics, journalRemark=null, publicationField=null, createdTime=1790588244275, updatedTime=1790588826779, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=D, firstLetterEn=D, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=eIT+4m2KVWPyCt/9B7VJoQ==, picEn=0WQPu/LDoP9XKci/CSo2YQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1311387845575668074, language=CN, name=地质力学学报, 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=1790588826793, updatedTime=1790588826793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.manuscripts.com.cn/dzlxxb, submissionEditorUrl=http://www.manuscripts.com.cn/dzlxxb, submissionReviewUrl=http://www.manuscripts.com.cn/dzlxxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1311387845621805419, language=EN, name=Journal of Geomechanics, 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=1790588826804, updatedTime=1790588826804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.manuscripts.com.cn/dzlxxb, submissionEditorUrl=http://www.manuscripts.com.cn/dzlxxb, submissionReviewUrl=http://www.manuscripts.com.cn/dzlxxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1311385891987619962, websiteList=[Website(id=1311386135344021834, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1311385891987619962, 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/dzlxxb/CN, language=CN, createTime=1790588419042, createBy=18614031015, updateTime=1790590359122, updateBy=18614031015, name=地质力学学报-中文, tplId=1146099689490845704, title=地质力学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1311394384663371943, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=articleTextType, value=kx, createTime=1790590385833, updateTime=1790590385833, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384629817508, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=banner, value=null, createTime=1790590385825, updateTime=1790590385825, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384705314986, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=grayFlag, value=0, createTime=1790590385843, updateTime=1790590385843, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384621428899, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=logo, value=https://castjournals.cast.org.cn/joweb/dzlxxb/CN/file/pic?fileId=FHk8j02jpAUqJCuAXgNz+g==, createTime=1790590385823, updateTime=1790590385823, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384734675116, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=minRunFlag, value=0, createTime=1790590385850, updateTime=1790590385850, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384654983334, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dzlxxb/CN/file/pic, createTime=1790590385831, updateTime=1790590385831, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384717897899, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=silenceFlag, value=0, createTime=1790590385846, updateTime=1790590385846, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384642400421, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1790590385828, updateTime=1790590385828, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384675954856, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=themeColor, value=null, createTime=1790590385836, updateTime=1790590385836, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394384688537769, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135344021834, code=themeStyle, value=null, createTime=1790590385839, updateTime=1790590385839, creator=18614031015, updator=18614031015)]), Website(id=1311386135411130720, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1311385891987619962, 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/dzlxxb/EN, language=EN, createTime=1790588419058, createBy=18614031015, updateTime=1790590353865, updateBy=18614031015, name=地质力学学报-英文, tplId=1146101810881728533, title=Journal of Geomechanics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1311394354476966043, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=articleTextType, value=kx, createTime=1790590378636, updateTime=1790590378636, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354455994520, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=banner, value=null, createTime=1790590378631, updateTime=1790590378631, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354497937566, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=grayFlag, value=0, createTime=1790590378641, updateTime=1790590378641, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354447605911, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=logo, value=https://castjournals.cast.org.cn/joweb/dzlxxb/EN/file/pic?fileId=FHk8j02jpAUqJCuAXgNz+g==, createTime=1790590378629, updateTime=1790590378629, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354514714784, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=minRunFlag, value=0, createTime=1790590378645, updateTime=1790590378645, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354468577434, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dzlxxb/EN/file/pic, createTime=1790590378634, updateTime=1790590378634, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354506326175, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=silenceFlag, value=0, createTime=1790590378643, updateTime=1790590378643, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354464383129, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1790590378633, updateTime=1790590378633, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354485354652, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=themeColor, value=null, createTime=1790590378638, updateTime=1790590378638, creator=18614031015, updator=18614031015), WebsiteProps(id=1311394354489548957, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135411130720, code=themeStyle, value=null, createTime=1790590378639, updateTime=1790590378639, creator=18614031015, updator=18614031015)])], journalTitle=地质力学学报, weixinUrl=null, journalUrl=https://journal.geomech.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Geomechanics, journalPhotoCn=eIT+4m2KVWPyCt/9B7VJoQ==, journalPhotoEn=0WQPu/LDoP9XKci/CSo2YQ==, journalFirstLetter=D, 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/dzlxxb/CN/10.12090/j.issn.1006-6616.2025108, detailUrlEn=https://castjournals.cast.org.cn/joweb/dzlxxb/EN/10.12090/j.issn.1006-6616.2025108, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dzlxxb/CN/PDF/10.12090/j.issn.1006-6616.2025108, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dzlxxb/EN/PDF/10.12090/j.issn.1006-6616.2025108, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1772208000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
融合层序地层先验信息的测井岩相智能识别方法
张明迪 1 , 李蒙 2, * , 刘远洋 1 , 黄渊 2 , 崔书岳 2
地质力学学报 | 2026,32(1): 245-257
收起
收藏切换
地质力学学报 | 2026 , 32 (1) : 245 -257
融合层序地层先验信息的测井岩相智能识别方法
全屏
[Author(id=1328032090005811929, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangmingdi.xnyq@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032091717087963, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032090005811929, language=EN, stringName=Mingdi ZHANG, firstName=Mingdi, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032091796779740, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032090005811929, language=CN, stringName=张明迪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国石油化工股份有限公司西南油气分公司,成都 610041, bio={"content":"

张明迪(1982—),男,硕士,副研究员,主要从事川东北地区油气藏工程、流体相态、油气藏渗流、高含硫油气开发等方面研究。Email:

"}, bioImg=null, bioContent=

张明迪(1982—),男,硕士,副研究员,主要从事川东北地区油气藏工程、流体相态、油气藏渗流、高含硫油气开发等方面研究。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089779319506, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=1, ext=[AuthorCompanyExt(id=1328032089787708115, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China), AuthorCompanyExt(id=1328032089800291028, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国石油化工股份有限公司西南油气分公司,成都 610041)])]), Author(id=1328032091868082910, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=limeng.syky@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1328032091947774688, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032091868082910, language=EN, stringName=Meng LI, firstName=Meng, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092052632289, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032091868082910, language=CN, stringName=李蒙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089892565717, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=2, ext=[AuthorCompanyExt(id=1328032089913537238, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China), AuthorCompanyExt(id=1328032089921925847, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206)])]), Author(id=1328032092123935459, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=182518415@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032092216210149, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092123935459, language=EN, stringName=Yuanyang LIU, firstName=Yuanyang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092308484838, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092123935459, language=CN, stringName=刘远洋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国石油化工股份有限公司西南油气分公司,成都 610041, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089779319506, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=1, ext=[AuthorCompanyExt(id=1328032089787708115, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China), AuthorCompanyExt(id=1328032089800291028, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089779319506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国石油化工股份有限公司西南油气分公司,成都 610041)])]), Author(id=1328032092400759528, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=huangyuan.syky@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032092480451306, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092400759528, language=EN, stringName=Yuan HUANG, firstName=Yuan, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092560143083, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092400759528, language=CN, stringName=黄渊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089892565717, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=2, ext=[AuthorCompanyExt(id=1328032089913537238, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China), AuthorCompanyExt(id=1328032089921925847, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206)])]), Author(id=1328032092669194989, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cuisy.syky@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1328032092761469679, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092669194989, language=EN, stringName=Shuyue CUI, firstName=Shuyue, middleName=null, lastName=CUI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1328032092836967152, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, authorId=1328032092669194989, language=CN, stringName=崔书岳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1328032089892565717, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, xref=2, ext=[AuthorCompanyExt(id=1328032089913537238, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China), AuthorCompanyExt(id=1328032089921925847, tenantId=1146029695717560320, journalId=1311385891987619962, articleId=1328032087535366847, companyId=1328032089892565717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国石油化工股份有限公司石油勘探开发研究院,北京 102206)])])]
张明迪1 , 李蒙2, * , 刘远洋1 , 黄渊2 , 崔书岳2
作者信息
  • 1中国石油化工股份有限公司西南油气分公司,成都 610041
  • 2中国石油化工股份有限公司石油勘探开发研究院,北京 102206
通讯作者:
李蒙(1988—),男,博士,副研究员,主要从事地球物理和人工智能交叉学科研究。Email:
作者简介:

张明迪(1982—),男,硕士,副研究员,主要从事川东北地区油气藏工程、流体相态、油气藏渗流、高含硫油气开发等方面研究。Email:

An intelligent lithofacies identification method for well logging of deep carbonate rocks incorporating sequence stratigraphic prior information
Mingdi ZHANG1 , Meng LI2, * , Yuanyang LIU1 , Yuan HUANG2 , Shuyue CUI2
Affiliations
  • 1Sinopec Southwest China Petroleum Bureau, Chengdu 610041, Sichuan, China
  • 2Sinopec Petroleum Exploration and Production Research Institute, Beijing 102206, China
出版时间: 2026-02-28 doi: 10.12090/j.issn.1006-6616.2025108
文章导航
收藏切换

岩相识别是储层表征的核心环节,对油气勘探开发具有重要意义。传统岩相识别主要依赖专家经验和人工解释,存在主观性强、效率低、一致性差等问题。文章针对碳酸盐岩生物礁、生屑滩等复杂岩相识别工作量大、精度低的难题,提出了一种层序地层先验约束下的深层碳酸盐岩测井岩相智能识别方法。该方法创新性地将层序地层学理论与深度学习技术深度融合,通过双分支神经网络架构分别提取测井响应特征和层序地层约束信息,并在特征空间实现有机融合,使模型在学习测井曲线数值模式的同时,遵循层序格架内岩相空间配置规律和垂向演化序列,有效解决了纯数据驱动方法易产生地质不合理预测的问题。方法采用自然伽马、声波时差、密度、电阻率等常规测井曲线及层序划分方案作为输入,利用卷积神经网络提取多尺度特征,通过长短时记忆模块(LSTM)实现岩相纵向演化的时序依赖关系建模。针对碳酸盐岩礁滩体发育规模,优选40 m样本长度以完整覆盖礁基−礁核−礁盖垂向序列或海平面旋回控制的沉积组合,并采用滑动时窗加权平均预测策略提升结果稳定性。元坝气田长兴组测井岩相识别应用表明,相比常规LSTM方法,新方法识别结果符合礁体演化规律,单井预测时间仅需5~10秒,效率较人工解释提升2~3个数量级,实现了岩相识别的自动化、智能化和地质合理化。

测井岩相识别  /  智能  /  层序地层先验  /  识别效率  /  识别精度
Objective

Lithofacies identification constitutes a core component of reservoir characterization and is of great significance for oil and gas exploration and development. Traditional lithofacies identification relies primarily on expert experience and manual interpretation, suffering from high subjectivity, low efficiency, and poor consistency. Moreover, identifying carbonate lithofacies such as bioreefs and bioclastic shoals solely through geological and geophysical data combined with limited core samples and thin-section analysis is labor-intensive and cannot meet the requirements of refined oil and gas field development. This study aims to address the major challenges in intelligent lithofacies identification, namely the insufficient modeling of spatial dependencies in the depth direction, the lack of technical prior knowledge, and the inadequate integration of geological understanding with data-driven approaches.

Methods

We propose an intelligent well-logging lithofacies identification method for deep carbonate rocks that integrates sequence stratigraphic prior information. The method applies a deep neural network, termed Sequence-Constrained Long Short-Term Memory Network (SC-LSTM), as its core framework. This network embeds sequence stratigraphic units as geological constraints into the input feature space of the model, achieving an organic integration of geological understanding with logging response characteristics. The network architecture comprises two parallel feature extraction modules: a curve feature extraction module that utilizes convolutional layers to extract local patterns and depth-directional variation characteristics from logging responses, and a sequence feature extraction module that performs convolutional encoding on sequence division schemes to convert discrete sequence and system tract information into continuous feature representations. The method uses conventional well logs, including natural gamma ray, acoustic transit time, density, neutron, and resistivity as input data. A sliding time-window sampling strategy expands the training dataset to address the problem of limited labeled samples, while a weighted averaging prediction method enhances the stability and reliability of the identification results.

Results

The application to the Changxing Formation carbonate reservoir in the Yuanba gas field demonstrates that an optimal sample length of 40 meters can (i) completely cover the vertical evolution sequence from reef base to reef core to reef cap, or (ii) encompass a complete reef-shoal depositional combination controlled by sea-level cycles. This, enables the model to fully learn the orderly stacking patterns and facies transition characteristics within sequence units. The model achieved 92% identification accuracy on the test set. Comparative experiments between conventional LSTM and SC-LSTM networks reveal that the proposed method effectively avoids geologically unreasonable predictions that may arise from relying solely on logging response characteristics. For example, it avoids erroneously predicting reef cap facies during the early highstand system tract or misidentifying reef cap facies as reef/shoal interfacies at reef tops.

Conclusions

These findings confirm that the integration of sequence stratigraphic prior information can effectively constrain model predictions and avoid geologically unreasonable results. The conventional LSTM model learns lithofacies characteristics only from numerical patterns of logging curves and easily confuses lithofacies types with similar logging responses under different sequence backgrounds. In contrast, the SC-LSTM model enables the network to understand the geological rules and the combined characteristics of lithofacies development within different sequence units and system tracts by fusing sequence stratigraphic information. This improves the geological rationality and prediction accuracy of lithofacies identification. [Significance] The significance of this study lies not only in its practical applications—enabling rapid establishment of regional lithofacies distribution patterns to guide well deployment and providing timely support for reservoir fine characterization and the exploitation of remaining oil and gas potential through the real-time updating of lithofacies interpretation schemes as new well data accumulate—but also in its theoretical contributions. It particularly advances the integration of domain knowledge with artificial intelligence technology by linking sequence stratigraphy theory, depositional environment evolution, and deep learning algorithms in a unified framework for intelligent lithofacies identification. This opens new avenues for automated and intelligent reservoir characterization in complex carbonate formations.

well logging lithofacies identification  /  intelligent identification  /  sequence stratigraphic prior information  /  deep learning  /  carbonate reservoir; SC-LSTM
张明迪, 李蒙, 刘远洋, 黄渊, 崔书岳. 融合层序地层先验信息的测井岩相智能识别方法. 地质力学学报, 2026 , 32 (1) : 245 -257 . DOI: 10.12090/j.issn.1006-6616.2025108
Mingdi ZHANG, Meng LI, Yuanyang LIU, Yuan HUANG, Shuyue CUI. An intelligent lithofacies identification method for well logging of deep carbonate rocks incorporating sequence stratigraphic prior information[J]. Journal of Geomechanics, 2026 , 32 (1) : 245 -257 . DOI: 10.12090/j.issn.1006-6616.2025108
岩相识别是油气勘探开发中的核心技术环节之一(陈程等,2024;陈科等,2025),直接关系到储层评价、油气产能预测和开发方案设计的准确性(李昌等,2021)。随着油气勘探向深层、超深层和复杂地质条件延伸,碳酸盐岩等非均质性强的储层岩相识别面临着前所未有的挑战(李昌等,2020;张红英等,2020;路菁等,2024;张涛,2025)。准确、高效的岩相识别技术已成为制约油气勘探开发效率提升的瓶颈。传统的人工解释方法主要依靠地质专家的经验知识,基于多条测井曲线的形态、幅度等特征判断岩相类型。这种方法解释效率较低,往往需要数天甚至数周时间才能完成工区内数十口井的岩相解释工作;由于不同解释人员的知识背景和经验差异,解释结果存在主观性,一致性难以保证。特别是在面对大规模井群岩相解释任务时,人工方法的局限性更加凸显,严重制约了油气勘探开发的进度和质量(王民等,2023;陈秀娟等,2024)。
随着人工智能技术的快速发展,基于机器学习的测井岩相自动分类方法成为研究热点(李宁等,2021;张国印等,2024)。从早期的支持向量机、随机森林等传统机器学习算法(韩文龙等,2016;赵忠军等,2016;Bhattacharya and Mishra,2018;Al-Mudhafar, 2020;Ippolito et al.,2021 ;何贤宏等,2023;Rathore et al.,2023;谌丽等,2023;王民等,2023),到深度神经网络、卷积神经网络(高飞等,2024)、循环神经网络等深度学习方法(Tian et al.,2021a;齐春生等,2023;Gao et al.,2025;张云骥,2025),再到融合注意力机制、生成对抗网络等前沿技术,测井岩相识别技术经历了从浅层到深层、从单一到多元、从静态到动态的发展历程(张国印等,2024;王丽媛等,2025)。这些方法在不同地质环境和储层类型中得到了广泛应用,包括碎屑岩(赵忠军等,2016;Bhattacharya and Mishra,2018;Al-Mudhafar,2020;Antariksa et al.,2022;Datta et al.,2023;Rathore et al.,2023; 黄千玲等,2024;Abuzeid et al.,2025;孟圆等,2025)、致密砂岩(Zhao et al.,2022;董少群等,2024;曹脊翔等,2025;赖锦等,2025;赵天沛,2025)、碳酸盐岩(李昌等,2021;何贤宏等,2023;Hou et al.,2024;路菁等,2024)、页岩(王民等,2023;刘粤蛟等,2025;闫佳飞等,2025)、河湖相(Zheng et al.,2022)等多种沉积环境,在裂缝识别方面也取得了重要进展(Tian et al.,2021a)。
尽管测井岩相自动分类技术取得了显著进展,但现有方法仍普遍存在一些关键问题亟待解决。一是空间依赖性建模不足,大多数方法忽略了测井曲线在深度方向的形态变化特征以及相邻层位间的地质关联性,难以充分利用地质序列的垂直和横向相关性。二是缺乏专业领域先验知识约束,专业领域知识与人工智能技术的融合程度不足(张国印等,2024;王丽媛等,2025)。需要进一步加强多模态数据融合并更好地融合地质先验知识,以推动测井岩相智能识别技术向更高精度、更强泛化、更好解释的方向发展。
针对上述问题,此次研究以元坝气田长兴组碳酸盐岩礁滩储层为研究对象,提出了SC-LSTM(Sequence Constrained Long Short-Term Memory Network)智能识别方法。该方法的技术路线包括:①构建双分支神经网络架构,分别提取测井响应特征和层序地层约束信息,在特征空间实现融合,将“沉积微相受控于层序地层格架”的地质认识嵌入模型学习过程;②以常规测井曲线(自然伽马、声波时差、密度、中子、深浅侧向电阻率)和层序划分方案为输入,利用卷积神经网络提取多尺度特征,通过LSTM网络建模岩相纵向演化的时序依赖关系;③根据礁滩体发育规模和沉积旋回厚度优化样本长度参数,采用滑动时窗加权平均预测策略提升结果的地质连续性和稳定性;④针对岩芯标定样本有限的问题,设计基于滑动时窗的数据增强方案,充分挖掘有限样本中的地质规律信息。
融合层序地层先验信息的沉积微相智能识别网络架构设计如图1所示。网络输入包括标准化处理后的测井曲线和层序划分方案,后者包含层序单元和体系域信息,通常在井间具有可对比性。层序划分方案的标准化处理流程包含由深到浅进行数字化编号及归一化处理。 以长兴组的4个四级层序为例,自深部到浅部依次命名为PSQ1、PSQ2、PSQ3、PSQ4。数字化编码采用插值赋值方式:在PSQ1层序深度范围内进行0~1的线性插值赋值,PSQ2为1~2,PSQ3为2~3,PSQ4为3~4,形成一条连续的层序编码曲线。随后对整体编码值进行归一化处理,将[0,4]区间映射至[0,1]区间,归一化公式为
$x_{norm}=x_{encoded}/4 ,$
其中$x_{encoded} $为插值赋值后的编码值,$x_{norm} $为归一化后的值。该标准化方法生成一根代表层序地层信息的数字化井曲线,既保留了层序的相对位置信息和层序界面的突变特征,又确保了不同井间的数值可比性。网络包含2个特征提取模块:曲线特征提取模块利用卷积层提取测井响应的局部模式和深度方向上的变化特征,经激活函数处理后输出曲线特征向量;层序特征提取模块对层序划分方案进行卷积编码,将离散的层序和体系域信息转换为连续特征表示,经激活函数处理后输出层序特征向量。特征融合模块接收来自2个并行分支的特征向量,通过拼接加权融合将曲线特征与层序特征整合,生成融合了地质先验知识的综合特征表示。这种融合机制避免了纯测井数据驱动下的预测不合理性。融合特征随后输入LSTM分类神经网络。LSTM网络利用其记忆单元和门控机制,沿深度方向建模岩相的纵向演化序列,捕捉相变的转换模式和长距离依赖关系。网络最终在每个深度点输出沉积微相的分类结果,实现从测井曲线到岩相识别的端到端预测。
样本标签来源于岩芯标定下对少数井测井数据的岩相解释。由于取芯成本高昂,岩芯数量有限,单个油田高质量岩相解释方案数量往往较少,难以满足传统方式深度学习训练需求。针对标注样本有限问题,采用滑动时窗采样策略扩充训练数据集,充分挖掘现有的有限样本中所蕴含的地质规律信息。滑动时窗采样是在连续的测井数据序列上以固定步长移动1个预设长度的时间窗口,每次移动生成1个新的训练样本。对于长度为L的测井序列,设置窗口长度为W,滑动步长为S,则可以生成(L−W)/S+1个子序列样本。每个时窗内包含W个连续深度点的测井数据和层序信息作为输入特征,对应的岩相标签作为监督信号。根据4个典型的滑动窗口(观测数据1~4;图2),每个窗口提取一段连续的测井曲线片段,并与相应的岩相标签(标签1~4)建立对应关系。
滑动时窗策略能够显著提升数据利用效率。以原始单井数据为例,假设单井有效测井深度为1000 m,采样间隔为0.125 m,共8000个数据点。若不采用滑动窗口,仅能提供1个完整序列样本;而采用窗口长度为64、步长为8的滑动采样策略,则可生成近1000个训练样本,数据量扩增了2个数量级。
该采样策略具有3个优势:①保持了序列连续性,滑动窗口内测井数据保持了原始纵向地质序列关系,有利于网络学习岩相垂向演化规律;②提高了泛化能力,通过窗口滑动,网络能够学习到不同深度段的岩相特征模式;③充分利用信息,滑动采样最大化挖掘每个标定井段信息。
影响模型训练效果的因素众多,文章着重聚焦样本长度参数,深入探究对预测精度影响规律。样本长度应与实际地质体的发育规模和沉积旋回特征相匹配。合适的样本长度应能够完整反映一个或多个沉积旋回的岩相组合特征和纵向演化规律,在捕捉层序地层单元内岩相在垂向上的韵律性变化过程中起关键作用。如果样本过短,可能仅覆盖单一岩相段或半个沉积旋回,无法充分体现测井曲线形态所指示的沉积环境演变过程,导致模型难以理解岩相纵向上的有序叠置关系、递变序列特征以及准层序组的韵律性变化规律。相反,如果样本长度过长,能够覆盖完整的层序地层单元甚至跨越多个体系域,但会导致可用训练样本数量减少,且包含过多岩相类型和复杂相变关系,增加模型学习难度,降低模型的泛化能力。因此,样本长度的选择应综合考虑目标工区的层序地层发育特征、沉积旋回厚度、岩相垂向变化频率等地质因素。选择方式将在后续实例分析中结合具体地质条件详细探讨。
采用滑动时窗预测结合加权平均法的岩相识别方法,通过多次预测求取加权平均值来提高预测结果的稳定性和可靠性。首先,对连续的测井数据按照固定样本长度进行滑动时窗采样,相邻样本间设置一定的重叠区域,这种重叠设计符合沉积地层的连续叠置特征——任一深度点的岩相特征不仅受控于该点自身的沉积环境,还受到上下相邻层位沉积背景的影响。每个时窗样本通过训练好的SC-LSTM网络进行独立预测,获得对应的岩相识别结果。对于任意深度点,由于滑动采样的重叠特性,该点会被多个不同的时窗样本覆盖,相当于从不同的地质剖面尺度对同一位置的岩相进行多次判别,从而获得多个预测结果。最终采用加权平均法对同一深度点的多个预测结果进行融合,这一过程类似于地质综合解释中对多源信息的加权综合判断(图3)。
研究区元坝气田位于四川省广元市苍溪县及南充市阆中市境内(图4)。三维地震资料的处理解释证实元坝地区长兴组发育大型台地边缘生物礁滩沉积,储层叠合连片,预测有利礁滩体面积逾500 km2。长兴组早期长兴组一段主要位于开阔台地相带,发育滩间、生屑滩及砂屑滩沉积;长兴组二段主要位于台地边缘生物礁滩相带,发育滩间、生屑滩、生物礁沉积。测试与十余年的生产实践证实长兴组二段发育的4条生物礁带为油气高产富集带。
元坝气田长兴组常规测井项目主要包括深浅双侧向、补偿声波、补偿中子、岩性密度、自然伽马、自然电位及井径等,特殊测井项目主要包括自然伽马能谱、地层倾角、电成像、偶极声波等。为保障深度学习方法可有效推广至大多数井,考虑多数井具备的测井曲线类型,以及测井曲线与岩相相关性,主要利用声波时差、自然点位与深浅侧向电阻率曲线作为预测岩相的主要观测数据。
在模型训练过程中同步进行验证与测试,以确保模型的有效性和泛化能力。训练过程涉及3类关键参数的协同优化:样本特征参数、网络结构参数以及训练超参数。
在元坝地区长兴组气田15口井的数据分配充分考虑了礁滩相发育的空间差异性和地质代表性。训练集选取12口井,覆盖了主要礁滩发育带,包括礁核、礁盖、礁基、生屑滩及礁/滩间等典型沉积微相发育区,确保训练样本能够充分学习不同沉积环境下的岩相组合特征和测井响应模式;验证集包含2口井,分别位于台地边缘礁滩相带和台地内部礁/滩间相带,用于训练过程监控和参数调整;测试集选用1口位于台地边缘高能相带的井,该井具有高度地质代表性:①完整钻穿长兴组,揭示了从台地基底到顶部的完整沉积序列;②礁滩体垂向叠置关系清晰、相变频繁,涵盖了研究区主要的沉积微相类型组合;③测井曲线质量优良,微相标定可靠性强。该井作为测试样本能够全面检验模型对典型碳酸盐岩台地边缘礁滩沉积体系的识别能力。
针对元坝地区长兴组气田碳酸盐岩地层特征开展了样本长度优选实验。根据岩芯观察和测井相分析,目标层段单个礁体或滩体的垂向厚度主要分布在10~40 m之间,受海平面旋回控制的礁滩沉积组合厚度一般为25~60 m。碳酸盐岩礁滩相的纵向演化具有明显的阶段性:礁体生长初期多为礁基相,随着水体能量增强和造礁生物繁盛发育为礁核相,顶部受波浪改造形成礁盖相;生屑滩则在高能条件下快速堆积,与低能环境的礁/滩间相频繁交替。为完整捕捉这种相序演化规律,设计了从2.5 m到50 m共20组样本长度进行对比实验。
实验结果显示,20 m和40 m样本长度的模型性能明显优于其他方案(图5)。20 m样本长度基本对应单个礁体生长阶段或单期生屑滩沉积厚度,能够较好识别单一微相单元内的岩性变化特征;40 m样本长度则能够涵盖从礁基到礁盖的完整礁体垂向序列,或包含生屑滩与礁/滩间相的交替演化过程,充分反映海平面升降导致的沉积环境变化和相序转换规律,更符合碳酸盐岩台地礁滩沉积体系的垂向叠置特征。
综合考虑地质合理性与预测精度,最终选定40 m作为最优样本长度。该参数设置使单个训练样本能够完整覆盖一个海平面旋回控制的礁滩沉积组合,包含从低能环境(礁/滩间)到高能环境(礁核、生屑滩)再到相对低能环境的完整相序转换,有效捕捉了礁基−礁核−礁盖或生屑滩−礁/滩间等岩相的有序演化模式。同时,该长度设置避免了跨越层序界面导致的不同体系域礁滩相特征混淆问题,确保样本反映的是同一层序格架内受海平面变化控制的礁滩发育规律。
40 m样本长度对应的训练过程性能指标如图6。从损失函数变化曲线(图6a)可以看出,训练损失从初始的1.6左右快速下降,在前100个训练轮次内降至0.8,随后稳步收敛至0.7附近。验证损失与训练损失保持良好的同步性,最终稳定在0.8左右,且未出现上升趋势,表明模型成功学习了不同层序单元内礁滩相的分布规律和测井响应特征,未发生过拟合。验证精度和测试精度在训练过程中均持续上升(图6b),在150个训练轮次后分别收敛至0.85和0.92。测试精度的优异表现得益于测试井礁滩相叠置样式清晰、礁核与生屑滩等高能相带识别特征明显,以及预测过程中加权平均方法对局部异常值的有效抑制,而验证过程直接计算样本集精度,未采用加权平均策略,因此精度相对略低。这些结果证明了40 m样本长度设置能够有效平衡礁滩沉积旋回完整性与模型泛化能力的要求。
为确保方法的可复现性,制定了SC-LSTM模型的完整超参数配置方案(表1)。这些参数通过系统的网格搜索和交叉验证实验确定,在保证模型性能的同时兼顾了训练效率。
网络结构参数的设置遵循以下原则:①曲线特征提取分支采用较小的卷积核(3×1)以捕捉测井曲线的局部响应模式,层序特征提取分支采用较大的卷积核(5×1)以编码层序界面的突变特征;②LSTM隐藏层单元数设置为128,经实验验证该配置能够有效平衡模型的学习能力与计算效率,过小的单元数(如64)会导致欠拟合,过大的单元数(如256)则会增加过拟合风险且显著延长训练时间;③采用0.3的Dropout比率和早停策略防止过拟合。
训练超参数方面,采用Adam优化器配合动态学习率衰减策略,初始学习率设为0.001,当验证损失在10个轮次内未改善时将学习率减半,这种策略使模型能够在训练后期进行更精细的参数调整。针对元坝气田长兴组礁滩相样本分布不均衡的特点(礁核和生屑滩样本较多,礁/滩间相样本较少),在损失函数中引入类别权重机制,权重与各类别样本数量成反比,确保模型对少数类别具有足够的学习能力。
基于表1的参数配置,模型在NVIDIA A5000 GPU上的单次完整训练耗时约45分钟,训练完成后单井微相预测时间约5~10秒,满足油田实际应用的效率要求。
为展示层序地层先验信息对沉积微相智能识别效果的提升,分别对直井和水平井的微相识别结果进行对比分析(图7,图8)。输入数据是测井曲线(自然伽马、声波时差、密度、中子、电阻率等)和层序地层信息。层序地层信息来源于研究区地质研究成果,即基于钻井、测井和地震资料综合解释建立的层序地层格架,该格架将目标层段划分为不同的三级层序和体系域。在模型训练阶段,已标定微相的实钻井(训练井)同时提供了测井数据、层序地层信息和沉积微相标签;在预测阶段,待预测井(如图7中直井A和图8中水平井B)仅需输入测井曲线和该井穿越地层的层序单元信息,网络即可输出微相识别结果。图中的地震波形和相对阻抗剖面作为地质背景展示,用于直观理解井位在碳酸盐岩台地中的空间位置和地质构造关系,并非模型输入数据。
直井A的沉积微相识别结果对比如图7所示。该井位于碳酸盐岩台地边缘,钻穿长兴组。模型在井段下部预测出现了礁盖相(图7a)。但根据区域地质背景和岩芯标定结果,长兴组一段该深度范围对应高位体系域早期,主要发育滩相和滩间相,尚未进入礁体大规模发育阶段,也没有发生礁体暴露,不应出现礁盖相。这一预测结果与碳酸盐岩台地礁体垂向演化的基本规律(礁基、礁核、礁盖自下而上发育)不符。相比之下, SC-LSTM模型通过引入层序地层约束信息能够识别该井段所属的层序单元和体系域类型,从而避免了在高位体系域早期错误预测礁盖相的情况(图7b)。预测的微相组合、更加符合该层序格架内礁体发育的阶段性特征。
水平井B的微相识别结果对比如图8。该井为一口台地边缘近水平井,井眼轨迹主要沿长兴组1段礁滩体内部穿行。从常规LSTM预测结果可以看出(图8a),在井段前部(2920~2940 ms,地震剖面显示为相对低波阻抗区域)预测出大量的礁/滩间相(浅蓝色)。从沉积环境分析,在构造相对高部位发育的相对低波阻抗地层通常指示高孔储层单元。而礁/滩间相代表低能沉积环境,其沉积物通常为泥质灰岩或泥晶灰岩。根据该井的层序地层位置分析,该井段位于高位体系域晚期,对应礁体顶部发育阶段,应主要发育礁盖相而非礁/滩间相。SC-LSTM模型预测结果则更加合理(图8b):在该低波阻抗区域主要预测为礁盖相(橙色),礁/滩间相仅出现在井眼末端更深部位(2940 ms以下),该位置根据层序对比应已进入下伏地层,可能存在相对低能沉积区域,微相组合符合碳酸盐岩台地的层序地层发育规律和沉积相空间配置模式。
上述对比表明,层序地层先验信息的引入能够有效约束模型的预测结果,避免单纯依赖测井响应特征可能导致的地质不合理预测。常规LSTM模型仅从测井曲线的数值模式学习微相特征,容易将不同层序背景下具有相似测井响应的微相类型混淆;而SC-LSTM模型通过融合层序地层信息,使网络理解了不同层序单元和体系域内微相发育的地质规律和组合特征,从而提高了微相识别的地质合理性和预测精度。
SC-LSTM模型识别效果提升的关键在于:①网络架构设计更加合理,通过并行架构实现测井特征与层序信息的有效融合。通过层序约束确保了微相识别结果符合沉积相空间配置规律,如礁核主要发育在台地边缘高能带、礁/滩间相分布在台缘低能区域、礁盖相指示礁体顶部暴露阶段等地质认识,提高了识别结果的地质可信度;②关键参数优化,特别是样本长度的选择需要与研究区实际地质体的发育规模相匹配。针对碳酸盐岩台地礁滩体系的特点,通过参数实验确定40 m的最优样本长度;该长度能够完整覆盖礁基−礁核−礁盖的垂向演化序列或一个海平面旋回控制的礁滩沉积组合,使模型充分学习到层序单元内微相的有序叠置规律和相序转换特征。
SC-LSTM模型初步实现了快速、准确、地质合理的沉积微相智能识别,在油田勘探开发中应用前景广阔。在勘探早期,可以快速建立全区微相分布模式,指导开发井部署;在开发中后期,随着新井钻探和测井资料的不断积累,模型可以实时更新微相解释方案,为油藏工程师动态调整储层描述方案、优化剩余油挖潜措施提供及时支持。对于沉积相控型储层,准确的微相识别是理解储集空间分布、预测优质储层发育带的基础。传统的测井相分析流程依赖人工逐井解释,一口井的微相识别通常需要经验丰富的地质专家耗费2~3个工作日完成,包括测井曲线预处理、岩芯标定、典型相模式建立、逐层对比解释等环节;而针对一个包含50口井的区块进行系统微相研究,整个周期往往长达3~6个月。文章提出的深度学习方法能够大幅缩短从测井数据采集到微相成果输出的周期:模型训练完成后,单井微相预测仅需5~10 s,区块尺度的批量预测可在数小时内完成,相比传统方法效率提升2~3个数量级。新方法不仅显著降低了人工成本,还能提升油藏地质研究和开发决策的时效性——在新井钻探完成后即可快速获得微相解释结果,为后续的储层评价、完井方案优化、注采井网部署等决策提供及时的地质依据。
(1)文章研究提出的SC-LSTM网络通过引入层序地层先验信息改进了传统的基于长短期记忆网络(LSTM)的智能识别方法,并应用于元坝气田长兴组碳酸盐岩礁滩相的沉积微相识别。该方法将测井特征提取与层序地层约束相融合,有效解决了单纯依赖测井响应特征可能导致的地质不合理预测问题,使微相识别结果符合礁体垂向演化规律(礁基−礁核−礁盖)和层序格架内的微相空间配置模式,显著提升了沉积微相识别的地质合理性和准确性。
(2)通过系统的参数优化实验,包括测井数据的全局标准化处理、样本长度与礁滩体发育规模的匹配(40 m覆盖完整礁体序列或海平面旋回),以及滑动时窗加权平均预测方法,SC-LSTM模型在测试集上取得了92%的识别准确率。对比实验表明,相较于常规LSTM方法,SC-LSTM方法能够有效避免在高位体系域早期错误预测礁盖相、在礁体顶部将礁盖相误判为礁/滩间相等地质不合理现象,验证了层序约束对提升微相识别地质可信度的重要作用。
(3)相比传统人工解释方法,SC-LSTM方法实现了智能化和自动化,可快速建立区域微相分布模式,指导开发井优化部署;在开发过程中随新井资料快速更新微相解释方案,为储层精细描述、优质储层预测和剩余油气挖潜提供及时支持。
作者贡献声明:李蒙负责样本预处理、神经网络搭建、训练;张明迪负责资料收集、模型评价、预测结果应用;黄渊负责标准井岩相解释;刘远洋负责测井数据一致性处理;崔书岳负责人工智能算法调研。所有作者均阅读并同意稿件的提交和发表。
Author’s Contributions: LI Meng performed sample preprocessing, constructed and trained the neural network; ZHANG Mingdi conducted data collection, model evaluation, and applied the prediction results; HUANG Yuan participated in standard well facies interpretation; LIU Yuanyang was involved in well logging data consistency processing; CUI Shuyue conducted artificial intelligence algorithm research. All authors have read and approved the submission and publication of the manuscript.
利益冲突声明:本文所有作者声明本研究无任何利益冲突。
Conflict of Interests: All authors declare no conflict of interests.
  • 国家科技重大专项(2025ZD1408802)
参考文献 引证文献
排序方式:
1
ABUZEID A M, BAGHDADY A R, KASSEM A A, 2025. Automated lithofacies classification: a comprehensive machine learning approach in Shushan Basin reservoirs, Western Desert, Egypt[J]. Journal of African Earth Sciences, 223: 105487.
2
AL-MUDHAFAR W J, 2020. Integrating machine learning and data analytics for geostatistical characterization of clastic reservoirs[J]. Journal of Petroleum Science and Engineering, 195: 107837.
3
ANTARIKSA G, MUAMMAR R, LEE J, 2022. Performance evaluation of machine learning-based classification with rock-physics analysis of geological lithofacies in Tarakan Basin, Indonesia[J]. Journal of Petroleum Science and Engineering, 208: 109250.
4
BHATTACHARYA S, MISHRA S, 2018. Applications of machine learning for facies and fracture prediction using Bayesian Network Theory and Random Forest: case studies from the Appalachian basin, USA[J]. Journal of Petroleum Science and Engineering, 170: 1005-1017.
5
CAO J X, CHEN S Y, XIAO B Y, et al., 2025. Machine learning based diagenetic facies logging identification: a case of Shaximiao Formation in central Sichuan Basin[J]. Science Technology and Engineering, 25(21): 8858-8870. (in Chinese with English abstract)
6
CHEN C, WANG L, ZHAO W Y, et al., 2024. Seismic facies and sedimentary distribution characteristics of the Upper Carboniferous in the Ounan Depression, eastern Qaidam Basin[J]. Journal of Geomechanics, 30(3): 408-418. (in Chinese with English abstract)
7
CHEN K, WANG Y L, LU Y X, et al., 2025. Sedimentary characteristics of the Lower Cambrian Shuijingtuo Formation in the E’Xi trough and its petroleum geological significance[J]. Journal of Geomechanics, 31(4): 604-616. (in Chinese with English abstract)
8
CHEN X J, FENG Z T, ZENG F R, et al., 2024. Development status of logging-based lithology identification technology for shale formations[J]. Xinjiang Petroleum Geology, 45(6): 742-752. (in Chinese with English abstract)
9
DATTA D, SINGH G, SINGH S K, et al., 2023. Application of multivariate change detection in automated lithofacies classification from well-log data in a nonstationary subsurface[J]. Journal of Applied Geophysics, 215: 105094.
10
DONG S Q, ZENG L B, JI C Q, et al., 2024. A deep kernel method for fracture identification in ultra-deep tight sandstones using well logs[J]. Earth Science Frontiers, 31(5): 166-176. (in Chinese with English abstract)
11
GAO F, QU Z P, WEI Z, et al., 2024. Study on well-log lithofacies classification based on machine learning methods[J]. Progress in Geophysics, 39(3): 1173-1192. (in Chinese with English abstract)
12
GAO Y N, TIAN M, GRANA D, et al., 2025. Attention mechanism‐assisted recurrent neural network for well log lithology classification[J]. Geophysical Prospecting, 73(2): 628-649.
13
HAN W L, WANG Y B, GAO X D, et al., 2016. Identification of sedimentary microfacies based on BP neural network[J]. Coal Technology, 35(12): 114-116. (in Chinese with English abstract)
14
HE X H, LI K S, XU J C, et al., 2023. Application of log lithofacies classification model based on clustering-support vector classification method[J]. Well Logging Technology, 47(2): 129-137. (in Chinese with English abstract)
15
HOU X M, LIAN P Q, ZHAO J Y, et al., 2024. Identification of carbonate sedimentary facies from well logs with machine learning[J]. Petroleum Research, 9(2): 165-175.
16
HUANG Q L, ZHAO J L, BAI Q, et al., 2024. Automatic recognition of sedimentary microfacies based on Adaboost algorithm: taking the Shanxi Formation in Q zone of Longdong gas field as an example[J]. Geological Bulletin of China, 43(4): 658-666.
17
IPPOLITO M, FERGUSON J, JENSON F, 2021. Improving facies prediction by combining supervised and unsupervised learning methods[J]. Journal of Petroleum Science and Engineering, 200: 108300.
18
LAI J, SONG X Y, YANG X, et al., 2025. Research progresses of comprehensive well logging evaluation methods of tight gas sandstone reservoirs[J]. Acta Petrolei Sinica, 46(1): 220-235. (in Chinese with English abstract)
19
LI C, JIA J, SHEN A J, et al., 2020. New method for quantitative identification of carbonate lithofacies based on conventional logging curves and its application[J]. Progress in Geophysics, 35(5): 1792-1802. (in Chinese with English abstract)
20
LI C, SHEN A J, CHANG S Y, et al., 2021. Application and contrast of machine learning in carbonate lithofacies log identification: a case study of Longwangmiao Formation of MX area in Sichuan Basin[J]. Petroleum Reservoir Evaluation and Development, 11(4): 586-596. (in Chinese with English abstract)
21
LI N, NING B S, WU H L, et al., 2021. Application status and prospects of artificial intelligence in well logging and formation evaluation[J]. Acta Petrolei Sinica, 42(4): 508-522. (in Chinese with English abstract)
22
LIU Y J, LAI F Q, XU H, et al., 2025. Intelligent identification methods for shale lithology based on the coupling deeply of logging curves[J]. Bulletin of Geological Science and Technology, 44(1): 308-320. (in Chinese with English abstract)
23
LU J, LIU M, WANG X C, 2024. Log identification method of sedimentary microfacies in deep carbonate rocks by decision tree[J]. Well Logging Technology, 48(2): 179-189. (in Chinese with English abstract)
24
MENG Y, JAI G H, LI C H, et al., 2025. Logging identification and application of diagenetic facies of clastic reservoir by unsupervised learning technology: a case study of the Santai Formation in Zhanhua sag, Bohai Bay Basin[J]. Journal of Palaeogeography (Chinese Edition), 27(3): 746-762. (in Chinese with English abstract)
25
QI C S, DING L, JIAO X Y, et al., 2023. Automatic identification method of sedimentary microfacies based on bi-directional long short-term recurrent neural network: taking Dongfang B gas field in Yinggehai Basin as an example[J]. Science Technology and Industry, 23(5): 217-221. (in Chinese with English abstract)
26
RATHORE P W S, HUSSAIN M, MALIK M B, et al., 2023. Well log analysis and comparison of supervised machine learning algorithms for lithofacies identification in Pab Formation, Lower Indus Basin[J]. Journal of Applied Geophysics, 219: 105199.
27
SHEN L, WANG C Z, NING C Q, et al., 2023. Well-log lithofacies classification based on machine learning for Chang-7 member in Longdong area of Ordos Basin[J]. Petroleum Reservoir Evaluation and Development, 13(4): 525-536. (in Chinese with English abstract)
28
TIAN M, LI B T, XU H M, et al., 2021a. Deep learning assisted well log inversion for fracture identification[J]. Geophysical Prospecting, 69(2): 419-433.
29
TIAN M, OMRE H, XU H M, 2021b. Inversion of well logs into lithology classes accounting for spatial dependencies by using hidden Markov models and recurrent neural networks[J]. Journal of Petroleum Science and Engineering, 196: 107598.
30
WANG L Y, LIU H Q, CHENG C, et al., 2025. Research progress on intelligent identification methods for well logging lithofacies based on deep learning[J]. Progress in Geophysics, 40(4): 1773-1787. (in Chinese with English abstract)
31
WANG M, YANG J L, WANG X, et al., 2023. Identification of shale lithofacies by well logs based on random forest algorithm[J]. Earth Science, 48(1): 130-142. (in Chinese with English abstract)
32
YAN J F, LI S L, WEI Z D, et al., 2025. Shale lithofacies prediction method with well-logging data based on XGBoost algorithm[J]. Journal of Palaeogeography (Chinese Edition), 27(3): 763-776. (in Chinese with English abstract)
33
ZHANG G Y, LIN C Y, WANG Z Y, et al., 2024. Hybrid knowledge-driven and data-driven intelligent reservoir characterization and its research progress[J]. Progress in Geophysics, 39(1): 119-140. (in Chinese with English abstract)
34
ZHANG H Y, XIE B, YUAN Q, et al., 2020. Logging-based sedimentary microfacies identification of Changxing Formation, Damaoping structure, Sichuan Basin[J]. Natural Gas Exploration and Development, 43(2): 38-44. (in Chinese with English abstract)
35
ZHANG T, LI Y P, LI Z K, et al, 2025. Fractures identification of deep tight reservoir with well logging based on improved long short-term memory neural network[J]. Earth Science Frontiers, 32(5): 456-465. (in Chinese with English abstract)
36
ZHANG Y J, LI Q, CAI Y D, et al., 2025. Evaluation of coal macrolithotypes based on machine learning logging inversion: a case study of the No. 8 coal seam in the Benxi Formation, Jiaxian Block, Ordos Basin[J]. Geoscience, 39(5): 1427-1436. (in Chinese with English abstract)
37
ZHAO C J, JIANG Y L, WANG L J, 2022. Data-driven diagenetic facies classification and well-logging identification based on machine learning methods: a case study on Xujiahe tight sandstone in Sichuan Basin[J]. Journal of Petroleum Science and Engineering, 217: 110798.
38
ZHAO T P, 2025. Logging lithofacies identification of tight sandstone reservoir based on ensemble learning algorithm[J]. Offshore Oil, 45(2): 55-61. (in Chinese with English abstract)
39
ZHAO Z J, LIU Y, WANG F Q, et al., 2016. Classification of borehole braided river sedimentary microfacies based on support vector machine[J]. Well Logging Technology, 40(5): 637-642. (in Chinese with English abstract)
40
ZHENG D Y, HOU M C, CHEN A Q, et al., 2022. Application of machine learning in the identification of fluvial-lacustrine lithofacies from well logs: a case study from Sichuan Basin, China[J]. Journal of Petroleum Science and Engineering, 215: 110610.
41
曹脊翔, 陈思源, 肖柏夷, 等, 2025. 基于机器学习的致密砂岩储层成岩相测井识别: 以川中地区沙溪庙组一段为例[J]. 科学技术与工程, 25(21): 8858-8870.
42
陈程, 王利, 赵为永, 等, 2024. 柴东地区欧南凹陷上石炭统地震相及沉积展布特征[J]. 地质力学学报, 30(3): 408-418.
43
陈科, 王昱荦, 卢妍欣, 等, 2025. 鄂西海槽下寒武统水井沱组沉积特征及其油气地质意义[J]. 地质力学学报, 31(4): 604-616.
44
陈秀娟, 冯镇涛, 曾芙蓉, 等, 2024. 页岩地层测井岩性识别技术发展现状[J]. 新疆石油地质, 45(6): 742-752.
45
董少群, 曾联波, 冀春秋, 等, 2024. 超深层致密砂岩裂缝测井识别深度核方法[J]. 地学前缘, 31(5): 166-176.
46
高飞, 曲志鹏, 魏震, 等, 2024. 基于机器学习方法的测井岩相分类研究[J]. 地球物理学进展, 39(3): 1173-1192.
47
韩文龙, 王延斌, 高向东, 等, 2016. 基于BP神经网络的沉积微相识别[J]. 煤炭技术, 35(12): 114-116.
48
何贤宏, 李可赛, 许家铖, 等, 2023. 基于聚类-支持向量机算法的碳酸盐岩测井岩相识别模型与应用[J]. 测井技术, 47(2): 129-137.
49
黄千玲, 赵军龙, 白倩, 等, 2024. 基于Adaboost算法的沉积微相自动识别: 以陇东气田Q区山西组为例[J]. 地质通报, 43(4): 658-666.
50
赖锦, 宋翔羽, 杨薰, 等, 2025. 致密砂岩气储层测井综合评价技术研究进展[J]. 石油学报, 46(1): 220-235.
51
李昌, 贾俊, 沈安江, 等, 2020. 基于常规测井识别微生物碳酸盐岩岩相新方法及应用[J]. 地球物理学进展, 35(5): 1792-1802.
52
李昌, 沈安江, 常少英, 等, 2021. 机器学习法在碳酸盐岩岩相测井识别中应用及对比: 以四川盆地MX地区龙王庙组地层为例[J]. 油气藏评价与开发, 11(4): 586-596.
53
李宁, 徐彬森, 武宏亮, 等, 2021. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 42(4): 508-522.
54
刘粤蛟, 赖富强, 徐浩, 等, 2025. 基于测井曲线深程度耦合的页岩岩相智能识别方法[J]. 地质科技通报, 44(1): 308-320.
55
路菁, 刘秘, 王晓畅, 2024. 深层碳酸盐岩沉积微相决策树测井识别方法[J]. 测井技术, 48(2): 179-189.
56
孟圆, 贾光华, 李传华, 等, 2025. 基于无监督学习技术的碎屑岩储集层成岩相测井识别与应用: 以沾化凹陷三台组为例[J]. 古地理学报, 27(3): 746-762.
57
齐春生, 丁磊, 焦祥燕, 等, 2023. 基于双向长短时循环神经网络的沉积微相自动识别方法: 以莺歌海盆地东方B气田为例[J]. 科技和产业, 23(5): 217-221.
58
谌丽, 王才志, 宁从前, 等, 2023. 基于机器学习的鄂尔多斯盆地陇东地区长7段岩相测井识别方法[J]. 油气藏评价与开发, 13(4): 525-536.
59
王丽媛, 刘红岐, 程超, 等, 2025. 基于深度学习的测井岩相智能识别方法研究进展[J]. 地球物理学进展, 40(4): 1773-1787.
60
王民, 杨金路, 王鑫, 等, 2023. 基于随机森林算法的泥页岩岩相测井识别[J]. 地球科学, 48(1): 130-142.
61
闫佳飞, 李胜利, 魏泽德, 等, 2025. 基于XGBoost算法的页岩岩相测井预测方法[J]. 古地理学报, 27(3): 763-776.
62
张国印, 林承焰, 王志章, 等, 2024. 知识与数据融合驱动的油气藏智能表征及研究进展[J]. 地球物理学进展, 39(1): 119-140.
63
张红英, 谢冰, 袁倩, 等, 2020. 四川盆地大猫坪构造长兴组测井沉积微相识别[J]. 天然气勘探与开发, 43(2): 38-44.
64
张涛, 李艳萍, 李泽凯, 等, 2025. 基于改进长短记忆神经网络的深层致密储层裂缝测井识别[J]. 地学前缘, 32(5): 456-465.
65
张云骥, 李倩, 蔡益栋, 等, 2025. 基于机器学习测井反演的宏观煤岩类型评价: 以鄂尔多斯盆地佳县区块本溪组8号煤为例[J]. 现代地质, 39(5): 1427-1436.
66
赵天沛, 2025. 基于集成学习算法的致密砂岩储层测井岩相识别[J]. 海洋石油, 45(2): 55-61.
67
赵忠军, 刘烨, 王凤琴, 等, 2016. 基于支持向量机的辫状河测井沉积微相识别[J]. 测井技术, 40(5): 637-642.
2026年第32卷第1期
80
35
0
引用本文
BibTeX
文章信息
doi: 10.12090/j.issn.1006-6616.2025108
  • 接收时间:2025-08-08
  • 首发时间:2026-11-13
  • 出版时间:2026-02-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-08-08
  • 修回日期:2026-01-14
  • 录用日期:2026-01-16
基金
This research was financially supported by the National Science and Technology Major Project (Grant No. 2025ZD1408802).
国家科技重大专项(2025ZD1408802)
作者信息
    1中国石油化工股份有限公司西南油气分公司,成都 610041
    2中国石油化工股份有限公司石油勘探开发研究院,北京 102206

通讯作者:

李蒙(1988—),男,博士,副研究员,主要从事地球物理和人工智能交叉学科研究。Email:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dzlxxb/CN/10.12090/j.issn.1006-6616.2025108
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