Article(id=1261262693164527968, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1261262687258985194, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405660, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1722096000000, receivedDateStr=2024-07-28, revisedDate=1744646400000, revisedDateStr=2025-04-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1778638059178, onlineDateStr=2026-05-13, pubDate=1752768000000, pubDateStr=2025-07-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1778638059178, onlineIssueDateStr=2026-05-13, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1778638059178, creator=13701087609, updateTime=1778638059178, updator=13701087609, issue=Issue{id=1261262687258985194, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='20', pageStart='8317', pageEnd='8759', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1778638057769, creator=13701087609, updateTime=1778753106634, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1261745237240722095, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1261262687258985194, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1261745237240722096, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1261262687258985194, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=8424, endPage=8434, ext={EN=ArticleExt(id=1261262696117318004, articleId=1261262693164527968, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Prediction Method of Groundwater in Karst Strata Based on Distance-attribute Hybrid Clustering Combined with ConvLSTM Model, columnId=1156262729351549255, journalTitle=Science Technology and Engineering, columnName=Papers·Astronomy and Geosciences, runingTitle=null, highlight=null, articleAbstract=

To address the issue of inaccuracies in groundwater level predictions due to the insufficient consideration of groundwater-related factors, clustering methods for observation wells based on spatial distance, hydrogeological attributes, and a hybrid of distance and attributes were proposed. The significance of inter-well connectivity in groundwater level prediction was validated. Four models were designed, which were applied to simulate and predict groundwater levels in the karst water region of Jinan and compared with actual observations. The prediction results indicate that the combined model incorporating the connectivity characteristics of karst aquifers, known as convolution-long short-term memory(ConvLSTM), outperforms the traditional long short-term memory(LSTM) model. Among the models, the mix-multivariate-convolution-long short-term memory(M-MV-ConvLSTM) model, which accounts for wells of the same category based on the hybrid distance-attribute clustering results (characterized by strong connectivity), achieves the highest prediction accuracy and the smallest error. The average root mean square error is approximately 0.457, and the Nash-Sutcliffe efficiency is approximately 0.216, demonstrating a higher prediction accuracy than the traditional LSTM model. The research results is positioned to serve as a reference for real-time groundwater level prediction in karst regions.

, correspAuthors=Hu LI, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Ming GAO, Hu LI, Xin-jin LIU, Kang ZHANG, Jian-yong HAN), CN=ArticleExt(id=1261262715763438151, articleId=1261262693164527968, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于距离-属性混合聚类结合ConvLSTM模型的岩溶地层地下水预测方法, columnId=1156262730077163858, journalTitle=科学技术与工程, columnName=论文·天文学、地球科学, runingTitle=null, highlight=null, articleAbstract=

为解决因地下水相关因素未考虑充分而导致的模型对地下水位预测不准确的问题,提出观测井的空间位置距离聚类方法、水文地质属性聚类方法和距离-属性混合聚类方法,验证观测井间连通性在地下水位预测中的重要性。设计4种模型并分别对济南岩溶水域的地下水位进行模拟和预测并与实际观测值对比。预测结果表明:考虑岩溶含水层连通性特征的联合模型ConvLSTM(convolution-long short term memory)要优于传统的长短期记忆网络模型(long short term memory,LSTM)。其中考虑距离-属性混合聚类结果的同类别井(连通性强)的模型(mix-multivariate-convolution-long short term memory,M-MV-ConvLSTM)预测结果精度最高、误差最小,其平均均方根误差约为0.457,纳什效率系数约为0.216,预测准确度高于传统的LSTM预测模型。研究成果可为岩溶水域的实时地下水位预测提供借鉴。

, correspAuthors=李虎, authorNote=null, correspAuthorsNote=
* 李虎(1983—),男,汉族,山东济南人,博士,高级工程师。研究方向:轨道交通工程建设。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=LbwUO/taJROeO85nAZdplA==, magXml=OVi1dErp6FrQaRZdqz/ijQ==, pdfUrl=null, pdf=TqgCSmadEuQTI0lulpXJlA==, pdfFileSize=9124745, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=unIFyObjC7NW+rYDRREfuQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=IYqDiNgkLN803HtiKkLKAQ==, mapNumber=null, authorCompany=null, fund=null, authors=

高明(1998—),男,汉族,山东临沂人,硕士研究生。研究方向:隧道工程。E-mail:

, authorsList=高明, 李虎, 刘鑫锦, 张康, 韩健勇)}, authors=[Author(id=1261377041249780246, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ming.8660@foxmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1261377042772312608, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377041249780246, language=EN, stringName=Ming GAO, firstName=Ming, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1261377043300794923, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377041249780246, language=CN, stringName=高明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 山东建筑大学土木工程学院, 济南 250101, bio={"content":"

高明(1998—),男,汉族,山东临沂人,硕士研究生。研究方向:隧道工程。E-mail:

"}, bioImg=null, bioContent=

高明(1998—),男,汉族,山东临沂人,硕士研究生。研究方向:隧道工程。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1261377039085519349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, xref=1, ext=[AuthorCompanyExt(id=1261377039408480760, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377039085519349, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1261377039517532667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377039085519349, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 山东建筑大学土木工程学院, 济南 250101)])]), Author(id=1261377043774751291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Lihu1007@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1261377044609417796, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377043774751291, language=EN, stringName=Hu LI, firstName=Hu, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1261377045859320402, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377043774751291, language=CN, stringName=李虎, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 济南轨道交通集团有限公司, 济南 250014, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1261377040062792194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, xref=2, ext=[AuthorCompanyExt(id=1261377040327033351, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China), AuthorCompanyExt(id=1261377040465445385, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 济南轨道交通集团有限公司, 济南 250014)])]), Author(id=1261377047549624923, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1261377048296211038, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377047549624923, language=EN, stringName=Xin-jin LIU, firstName=Xin-jin, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1261377048791138918, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377047549624923, language=CN, stringName=刘鑫锦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 济南轨道交通集团有限公司, 济南 250014, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1261377040062792194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, xref=2, ext=[AuthorCompanyExt(id=1261377040327033351, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China), AuthorCompanyExt(id=1261377040465445385, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 济南轨道交通集团有限公司, 济南 250014)])]), Author(id=1261377049600639598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1261377051697791603, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377049600639598, language=EN, stringName=Kang ZHANG, firstName=Kang, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1261377052079473274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377049600639598, language=CN, stringName=张康, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 济南轨道交通集团有限公司, 济南 250014, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1261377040062792194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, xref=2, ext=[AuthorCompanyExt(id=1261377040327033351, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China), AuthorCompanyExt(id=1261377040465445385, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 济南轨道交通集团有限公司, 济南 250014)])]), Author(id=1261377052549235330, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1261377053887218319, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377052549235330, language=EN, stringName=Jian-yong HAN, firstName=Jian-yong, middleName=null, lastName=HAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1261377054944182932, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, authorId=1261377052549235330, language=CN, stringName=韩健勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 山东建筑大学土木工程学院, 济南 250101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1261377039085519349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, xref=1, ext=[AuthorCompanyExt(id=1261377039408480760, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377039085519349, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1261377039517532667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377039085519349, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 山东建筑大学土木工程学院, 济南 250101)])])], keywords=[Keyword(id=1261377057024557734, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, orderNo=1, keyword=groundwater level prediction), Keyword(id=1261377057863418544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, orderNo=2, keyword=long short term memory network(LSTM)), Keyword(id=1261377058731639487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, orderNo=3, keyword=cluster), Keyword(id=1261377060929454790, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, orderNo=4, keyword=karst aquifer), Keyword(id=1261377061730566861, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, orderNo=1, keyword=地下水位预测), Keyword(id=1261377063009829592, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, orderNo=2, keyword=长短期记忆网络(LSTM)), Keyword(id=1261377065048261345, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, orderNo=3, keyword=聚类), Keyword(id=1261377065576743659, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, orderNo=4, keyword=岩溶含水层)], refs=[Reference(id=1261377085214474257, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=27, pageStart=11919, pageEnd=11927, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=张召悦, 张红波, journalName=科学技术与工程, refType=null, unstructuredReference=张召悦, 张红波. 基于ARMA-AE-LSTM模型的进场交通流预测方法[J]. 科学技术与工程, 2024, 24(27): 11919-11927., articleTitle=基于ARMA-AE-LSTM模型的进场交通流预测方法, refAbstract=null), Reference(id=1261377087391318039, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=27, pageStart=11919, pageEnd=11927, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Zhang Zhaoyue, Zhang Hongbo, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Zhaoyue, Zhang Hongbo. Approach traffic flow prediction method based on ARMA-AE-LSTM Model[J], Science Technology and Engineering, 2024, 24(27): 11919-11927., articleTitle=Approach traffic flow prediction method based on ARMA-AE-LSTM Model, refAbstract=null), Reference(id=1261377087827525660, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=8, pageStart=69, pageEnd=75, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=孙虹洁, 赵振华, 黄林显, journalName=人民黄河, refType=null, unstructuredReference=孙虹洁, 赵振华, 黄林显, . 多变量LSTM神经网络模型在地下水位预测中的应用[J]. 人民黄河, 2022, 44(8): 69-75., articleTitle=多变量LSTM神经网络模型在地下水位预测中的应用, refAbstract=null), Reference(id=1261377088221790242, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=8, pageStart=69, pageEnd=75, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Sun Hongjie, Zhao Zhenhua, Hang Linxian, journalName=Yellow River, refType=null, unstructuredReference=Sun Hongjie, Zhao Zhenhua, Hang Linxian, et al. Application of multivariate LSTM neural network model in groundwater level prediction[J]. Yellow River, 2022, 44(8): 69-75., articleTitle=Application of multivariate LSTM neural network model in groundwater level prediction, refAbstract=null), Reference(id=1261377088540557353, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=9, pageStart=127, pageEnd=131, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=张朝逢, 陈皓锐, 岳中奇, journalName=中国农村水利水电, refType=null, unstructuredReference=张朝逢, 陈皓锐, 岳中奇. 基于长短时记忆网络(LSTM)的地下水埋深模拟预测——以关中平原为例的实例分析[J]. 中国农村水利水电, 2020(9): 127-131, 137., articleTitle=基于长短时记忆网络(LSTM)的地下水埋深模拟预测——以关中平原为例的实例分析, refAbstract=null), Reference(id=1261377088930627630, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=9, pageStart=127, pageEnd=131, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Zhang Chaofeng, Chen Haorui, Yue Zhongqi, journalName=China Rural Water and Hydropower, refType=null, unstructuredReference=Zhang Chaofeng, Chen Haorui, Yue Zhongqi. Simulation and prediction of groundwater depth based on long short-term memory network (LSTM): a case study of Guanzhong Plain[J]. China Rural Water and Hydropower, 2020(9): 127-131, 137., articleTitle=Simulation and prediction of groundwater depth based on long short-term memory network (LSTM): a case study of Guanzhong Plain, refAbstract=null), Reference(id=1261377089161314352, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2021, volume=29, issue=1, pageStart=112, pageEnd=122, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=陈守开, 蒋海峰, 李海瑞, journalName=应用基础与工程科学学报, refType=null, unstructuredReference=陈守开, 蒋海峰, 李海瑞, . 基于RST-LSTM模型的堤坝渗压动态预测分析[J]. 应用基础与工程科学学报, 2021, 29(1): 112-122., articleTitle=基于RST-LSTM模型的堤坝渗压动态预测分析, refAbstract=null), Reference(id=1261377089484275765, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2021, volume=29, issue=1, pageStart=112, pageEnd=122, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Chen Shoukai, Jiang Haifeng, Li Hairui, journalName=Journal of Basic Science and Engineering, refType=null, unstructuredReference=Chen Shoukai, Jiang Haifeng, Li Hairui, et al. Dynamic prediction analysis of dam seepage pressure based on RST-LSTM model[J]. Journal of Basic Science and Engineering, 2021, 29(1): 112-122., articleTitle=Dynamic prediction analysis of dam seepage pressure based on RST-LSTM model, refAbstract=null), Reference(id=1261377089870151739, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=4, pageStart=74, pageEnd=82, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=牛欣怡, 鲁程鹏, 卢佳赟, journalName=河海大学学报(自然科学版), refType=null, unstructuredReference=牛欣怡, 鲁程鹏, 卢佳赟, . 机器学习模型在地下水埋深模拟中的适应性分析[J]. 河海大学学报(自然科学版), 2022, 50(4): 74-82., articleTitle=机器学习模型在地下水埋深模拟中的适应性分析, refAbstract=null), Reference(id=1261377091866640449, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=4, pageStart=74, pageEnd=82, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Niu Xinyi, Lu Chengpeng, Lu Jiayun, journalName=Journal of Hohai University(Natural Sciences), refType=null, unstructuredReference=Niu Xinyi, Lu Chengpeng, Lu Jiayun, et al. Adaptability analysis of machine learning model in groundwater depth simulation[J]. Journal of Hohai University(Natural Sciences), 2022, 50(4): 74-82., articleTitle=Adaptability analysis of machine learning model in groundwater depth simulation, refAbstract=null), Reference(id=1261377092432871494, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=27, pageStart=11663, pageEnd=11673, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=陈聪, 候磊, 李乐乐, journalName=科学技术与工程, refType=null, unstructuredReference=陈聪, 候磊, 李乐乐, . 基于GRU改进RNN神经网络的飞机燃油流量预测[J]. 科学技术与工程, 2021, 21(27): 11663-11673., articleTitle=基于GRU改进RNN神经网络的飞机燃油流量预测, refAbstract=null), Reference(id=1261377092718084171, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=27, pageStart=11663, pageEnd=11673, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Chen Cong, Hou Lei, Li Lele, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Chen Cong, Hou Lei, Li Lele, et al. Prediction of aircraft fuel flow based on recurrent neural network[J]. Science Technology and Engineering, 2021, 21(27): 11663-11673., articleTitle=Prediction of aircraft fuel flow based on recurrent neural network, refAbstract=null), Reference(id=1261377092965548109, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=1, pageStart=208, pageEnd=216, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=闫佰忠, 孙剑, 王昕洲, journalName=吉林大学学报(地球科学版), refType=null, unstructuredReference=闫佰忠, 孙剑, 王昕洲, . 基于多变量LSTM神经网络的地下水水位预测[J]. 吉林大学学报(地球科学版), 2020, 50(1): 208-216., articleTitle=基于多变量LSTM神经网络的地下水水位预测, refAbstract=null), Reference(id=1261377093502419026, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=1, pageStart=208, pageEnd=216, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Yan Baizhong, Sun Jian, Wang Xinzhou, journalName=Journal of Jilin University(Earth Science Edition), refType=null, unstructuredReference=Yan Baizhong, Sun Jian, Wang Xinzhou, et al. Groundwater level prediction based on multivariate LSTM neural network[J]. Journal of Jilin University(Earth Science Edition), 2020, 50(1): 208-216., articleTitle=Groundwater level prediction based on multivariate LSTM neural network, refAbstract=null), Reference(id=1261377093796020311, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=10, pageStart=73, pageEnd=77, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=汪云, 杨海博, 徐建, journalName=节水灌溉, refType=null, unstructuredReference=汪云, 杨海博, 徐建, . 基于长短期记忆神经网络模型的地下水水位预测研究[J]. 节水灌溉, 2019(10): 73-77., articleTitle=基于长短期记忆神经网络模型的地下水水位预测研究, refAbstract=null), Reference(id=1261377094135758939, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=10, pageStart=73, pageEnd=77, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Wang Yun, Yang Haibo, Xun Jian, journalName=Water Saving Irrigation, refType=null, unstructuredReference=Wang Yun, Yang Haibo, Xun Jian, et al. Research on groundwater level prediction based on long short-term memory neural network model[J]. Water Saving Irrigation, 2019(10): 73-77., articleTitle=Research on groundwater level prediction based on long short-term memory neural network model, refAbstract=null), Reference(id=1261377094311919712, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=19, pageStart=7988, pageEnd=7998, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=冯希尧, 苟俊程, 刘瑞, journalName=科学技术与工程, refType=null, unstructuredReference=冯希尧, 苟俊程, 刘瑞, . 基于遗传算法优化机器学习模型的地下水潜在性预测[J]. 科学技术与工程, 2024, 24(19): 7988-7998., articleTitle=基于遗传算法优化机器学习模型的地下水潜在性预测, refAbstract=null), Reference(id=1261377094504857701, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=19, pageStart=7988, pageEnd=7998, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=Feng Xiyao, Gou Juncheng, Liu Rui, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Feng Xiyao, Gou Juncheng, Liu Rui, et al. Prediction of groundwater potential based on genetic algorithm optimized machine learning model[J]. Science Technology and Engineering, 2024, 24(19): 7988-7998., articleTitle=Prediction of groundwater potential based on genetic algorithm optimized machine learning model, refAbstract=null), Reference(id=1261377094865567850, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=6, pageStart=70, pageEnd=72, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=胡飞跃, 王忠忠, journalName=地下水, refType=null, unstructuredReference=胡飞跃, 王忠忠. 基于降雨量的SWA-LSTM深度学习模型在地下水位预测中的应用研究[J]. 地下水, 2022, 44(6): 70-72, 113., articleTitle=基于降雨量的SWA-LSTM深度学习模型在地下水位预测中的应用研究, refAbstract=null), Reference(id=1261377096379711598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=6, pageStart=70, pageEnd=72, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=Hu Feiyue, Wang Zhongzhong, journalName=Ground Water, refType=null, unstructuredReference=Hu Feiyue, Wang Zhongzhong. The application of SWA-LSTM deep learning model based on rainfall in groundwater level prediction[J]. Ground Water, 2022, 44(6): 70-72, 113., articleTitle=The application of SWA-LSTM deep learning model based on rainfall in groundwater level prediction, refAbstract=null), Reference(id=1261377096597815411, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=4, pageStart=92, pageEnd=98, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=侯金霄, 黄林显, 胡晓农, journalName=水资源与水工程学报, refType=null, unstructuredReference=侯金霄, 黄林显, 胡晓农, . 基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用[J]. 水资源与水工程学报, 2023, 34(4): 92-98., articleTitle=基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用, refAbstract=null), Reference(id=1261377096916582517, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=4, pageStart=92, pageEnd=98, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=Hou Jinxiao, Hang Linxian, Hu Xiaonong, journalName=Journal of Water Resources and Water Engineering, refType=null, unstructuredReference=Hou Jinxiao, Hang Linxian, Hu Xiaonong, et al. Application of karst groundwater level prediction in Baotu Spring based on EMD-LSTM coupling model[J]. Journal of Water Resources and Water Engineering, 2023, 34(4): 92-98., articleTitle=Application of karst groundwater level prediction in Baotu Spring based on EMD-LSTM coupling model, refAbstract=null), Reference(id=1261377097084354682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=4, pageStart=689, pageEnd=697, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=郭艺, 秦大军, 王枫, journalName=中国岩溶, refType=null, unstructuredReference=郭艺, 秦大军, 王枫, . 基于时间序列分析法的岩溶泉水位预测[J]. 中国岩溶, 2021, 40(4): 689-697., articleTitle=基于时间序列分析法的岩溶泉水位预测, refAbstract=null), Reference(id=1261377097185017980, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=4, pageStart=689, pageEnd=697, url=null, language=null, rfNumber=[12], rfOrder=23, authorNames=Guo Yi, Qin Dajun, Wang Feng, journalName=Carsologica Sinica, refType=null, unstructuredReference=Guo Yi, Qin Dajun, Wang Feng, et al. Prediction of karst spring water level based on time series analysis method[J]. Carsologica Sinica, 2021, 40(4): 689-697., articleTitle=Prediction of karst spring water level based on time series analysis method, refAbstract=null), Reference(id=1261377097268904063, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=4, pageStart=492, pageEnd=498, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=冯鹏宇, 金韬, 沈一选, journalName=计算机仿真, refType=null, unstructuredReference=冯鹏宇, 金韬, 沈一选, . 基于CNN-Transformer的城区地下水位预测[J]. 计算机仿真, 2023, 40(4): 492-498., articleTitle=基于CNN-Transformer的城区地下水位预测, refAbstract=null), Reference(id=1261377097419899008, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=4, pageStart=492, pageEnd=498, url=null, language=null, rfNumber=[13], rfOrder=25, authorNames=Feng Pengyu, Jin Tao, Shen Yixuan, journalName=Computer Simulation, refType=null, unstructuredReference=Feng Pengyu, Jin Tao, Shen Yixuan, et al. Prediction of urban groundwater level based on CNN-Transformer[J]. Computer Simulation, 2023, 40(4): 492-498., articleTitle=Prediction of urban groundwater level based on CNN-Transformer, refAbstract=null), Reference(id=1261377097524756612, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=31, issue=4, pageStart=961, pageEnd=976, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=张研, 郭道静, 张树光, journalName=应用基础与工程科学学报, refType=null, unstructuredReference=张研, 郭道静, 张树光, . 岩溶区灰岩溶蚀程度卷积神经网络识别及敏感性分析[J]. 应用基础与工程科学学报, 2023, 31(4): 961-976., articleTitle=岩溶区灰岩溶蚀程度卷积神经网络识别及敏感性分析, refAbstract=null), Reference(id=1261377097788997767, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=31, issue=4, pageStart=961, pageEnd=976, url=null, language=null, rfNumber=[14], rfOrder=27, authorNames=Zhang Yan, Guo Daojing, Zhang Shuguang, journalName=Journal of Basic Science and Engineering, refType=null, unstructuredReference=Zhang Yan, Guo Daojing, Zhang Shuguang, et al. Convolutional neural network identification and sensitivity analysis of limestone dissolution degree in karst area[J]. Journal of Basic Science and Engineering, 2023, 31(4): 961-976., articleTitle=Convolutional neural network identification and sensitivity analysis of limestone dissolution degree in karst area, refAbstract=null), Reference(id=1261377098153902219, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=32, pageStart=13665, pageEnd=13677, url=null, language=null, rfNumber=[15], rfOrder=28, authorNames=任青阳, 王彦丁, 施俭, journalName=科学技术与程, refType=null, unstructuredReference=任青阳, 王彦丁, 施俭. 卷积神经网络目标检测算法研究进展[J]. 科学技术与程, 2024, 24(32): 13665-13677., articleTitle=卷积神经网络目标检测算法研究进展, refAbstract=null), Reference(id=1261377098481057935, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=32, pageStart=13665, pageEnd=13677, url=null, language=null, rfNumber=[15], rfOrder=29, authorNames=Ren Qingyang, Wang Yanding, Shi Jian, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Ren Qingyang, Wang Yanding, Shi Jian. Advances in target detection algorithms for convolutional neural networks[J]. Science Technology and Engineering, 2024, 24(32): 13665-13677., articleTitle=Advances in target detection algorithms for convolutional neural networks, refAbstract=null), Reference(id=1261377098774659218, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=10, pageStart=74, pageEnd=75, url=null, language=null, rfNumber=[16], rfOrder=30, authorNames=郭靖, journalName=网络安全技术与应用, refType=null, unstructuredReference=郭靖. 对K-means聚类算法欧氏距离加权系数的研究[J]. 网络安全技术与应用, 2016(10): 74-75., articleTitle=对K-means聚类算法欧氏距离加权系数的研究, refAbstract=null), Reference(id=1261377099005345941, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=10, pageStart=74, pageEnd=75, url=null, language=null, rfNumber=[16], rfOrder=31, authorNames=Guo Jing, journalName=Network Security Technology & Application, refType=null, unstructuredReference=Guo Jing. Research on the Euclidean distance weighted coefficient of K-means clustering algorithm[J]. Network Security Technology & Application, 2016(10): 74-75., articleTitle=Research on the Euclidean distance weighted coefficient of K-means clustering algorithm, refAbstract=null), Reference(id=1261377100750176407, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=6, pageStart=162, pageEnd=166, url=null, language=null, rfNumber=[17], rfOrder=32, authorNames=金福喜, 袁权威, 秦帅帅, journalName=金属矿山, refType=null, unstructuredReference=金福喜, 袁权威, 秦帅帅. 基于GIS和K-means聚类方法的滑坡气象预警模型[J]. 金属矿山, 2018(6): 162-166., articleTitle=基于GIS和K-means聚类方法的滑坡气象预警模型, refAbstract=null), Reference(id=1261377100850839705, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=6, pageStart=162, pageEnd=166, url=null, language=null, rfNumber=[17], rfOrder=33, authorNames=Jin Fuxi, Yuan Quanwei, Qin Shuaishuai, journalName=Metal Mine, refType=null, unstructuredReference=Jin Fuxi, Yuan Quanwei, Qin Shuaishuai. Landslide meteorological early warning model based on GIS and K-means clustering method[J]. Metal Mine, 2018(6): 162-166., articleTitle=Landslide meteorological early warning model based on GIS and K-means clustering method, refAbstract=null), Reference(id=1261377100968280218, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2019, volume=2, issue=2, pageStart=226, pageEnd=235, url=null, language=null, rfNumber=[18], rfOrder=34, authorNames=Yuan C H, Yang H T, journalName=Multidisciplinary Scientific Journal, refType=null, unstructuredReference=Yuan C H, Yang H T. Research on K-value selection method of K-means clustering algorithm[J]. Multidisciplinary Scientific Journal, 2019, 2(2): 226-235., articleTitle=Research on K-value selection method of K-means clustering algorithm, refAbstract=null), Reference(id=1261377101106692252, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=23, pageStart=10146, pageEnd=10154, url=null, language=null, rfNumber=[19], rfOrder=35, authorNames=程亚南, 王晓峰, 刘凇佐, journalName=科学技术与工程, refType=null, unstructuredReference=程亚南, 王晓峰, 刘凇佐, . 求解多起点多旅行商问题的K-means聚类信息传播算法[J]. 科学技术与工程, 2022, 22(23): 10146-10154., articleTitle=求解多起点多旅行商问题的K-means聚类信息传播算法, refAbstract=null), Reference(id=1261377101320601759, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=23, pageStart=10146, pageEnd=10154, url=null, language=null, rfNumber=[19], rfOrder=36, authorNames=Cheng Yanan, Wang Xiaofeng, Liu Songzuo, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Cheng Yanan, Wang Xiaofeng, Liu Songzuo, et al. K-means clustering information propagation algorithm for multiple depots multiple traveling salesman problem[J]. Science Technology and Engineering, 2022, 22(23): 10146-10154., articleTitle=K-means clustering information propagation algorithm for multiple depots multiple traveling salesman problem, refAbstract=null), Reference(id=1261377101610008737, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=4, pageStart=1086, pageEnd=1093, url=null, language=null, rfNumber=[20], rfOrder=37, authorNames=蒋溢, 伍书平, 胡昆, journalName=计算机应用, refType=null, unstructuredReference=蒋溢, 伍书平, 胡昆, . 基于Lasso和构造性覆盖算法的不均衡数据分类方法[J]. 计算机应用, 2023, 43(4): 1086-1093., articleTitle=基于Lasso和构造性覆盖算法的不均衡数据分类方法, refAbstract=null), Reference(id=1261377101744226468, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=4, pageStart=1086, pageEnd=1093, url=null, language=null, rfNumber=[20], rfOrder=38, authorNames=Jiang Yi, Wu Shuping, Hu Kun, journalName=Journal of Computer Applications, refType=null, unstructuredReference=Jiang Yi, Wu Shuping, Hu Kun, et al. Imbalanced data classification method based on Lasso and constructive covering algorithm[J]. Journal of Computer Applications, 2023, 43(4): 1086-1093., articleTitle=Imbalanced data classification method based on Lasso and constructive covering algorithm, refAbstract=null)], funds=[Fund(id=1261377084073624572, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, awardId=G2022023020L, language=CN, fundingSource=国家外国专家项目(G2022023020L), fundOrder=null, country=null), Fund(id=1261377084509831170, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, awardId=2019JZZY020105, language=CN, fundingSource=山东省重大科技创新工程(2019JZZY020105), fundOrder=null, country=null), Fund(id=1261377084639854599, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, awardId=22YF7FH224, language=CN, fundingSource=甘肃省重点研发计划(22YF7FH224), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1261377039085519349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, xref=1, ext=[AuthorCompanyExt(id=1261377039408480760, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377039085519349, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1261377039517532667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377039085519349, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 山东建筑大学土木工程学院, 济南 250101)]), AuthorCompany(id=1261377040062792194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, xref=2, ext=[AuthorCompanyExt(id=1261377040327033351, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China), AuthorCompanyExt(id=1261377040465445385, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, companyId=1261377040062792194, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 济南轨道交通集团有限公司, 济南 250014)])], figs=[ArticleFig(id=1261377066772120321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.1, caption=Scope of the study area and the location of observation wells, figureFileSmall=KECg6u8KdGeGOgEGS8RxUw==, figureFileBig=Gj2geTEA8OmcwGL1tM+2cw==, tableContent=null), ArticleFig(id=1261377067254465290, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图1, caption=研究区范围和观测井位置

基于自然资源部标准地图服务网站审图号鲁SG(2024)035号的标准地图制作,底图无修改;No.1~No.16为水文观测井编号

, figureFileSmall=KECg6u8KdGeGOgEGS8RxUw==, figureFileBig=Gj2geTEA8OmcwGL1tM+2cw==, tableContent=null), ArticleFig(id=1261377067640341268, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.2, caption=Total flow chart of connectivity analysis, figureFileSmall=8IqLZITyj7PW+HfvUZ7xoQ==, figureFileBig=r/L+/bUPtRnNwPMqD2fABA==, tableContent=null), ArticleFig(id=1261377068001051416, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图2, caption=连通性分析总流程图, figureFileSmall=8IqLZITyj7PW+HfvUZ7xoQ==, figureFileBig=r/L+/bUPtRnNwPMqD2fABA==, tableContent=null), ArticleFig(id=1261377069502612253, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.3, caption=Surface DEM, figureFileSmall=ZjeijyNgiM5yt9RXtSzDJg==, figureFileBig=O/6EmFkQIVjh23kgfc+XAA==, tableContent=null), ArticleFig(id=1261377069754270496, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图3, caption=地表DEM, figureFileSmall=ZjeijyNgiM5yt9RXtSzDJg==, figureFileBig=O/6EmFkQIVjh23kgfc+XAA==, tableContent=null), ArticleFig(id=1261377069955597094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.4, caption=Flowchart of the clustering method, figureFileSmall=oJJ078iJPy791LhGue4+GA==, figureFileBig=Vd4qz1nftO+BuXPHj6KOQw==, tableContent=null), ArticleFig(id=1261377070320501550, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图4, caption=聚类方法流程图, figureFileSmall=oJJ078iJPy791LhGue4+GA==, figureFileBig=Vd4qz1nftO+BuXPHj6KOQw==, tableContent=null), ArticleFig(id=1261377070769292083, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.5, caption=Spatial location distance clustering results, figureFileSmall=0mT6bLNBxCEY+9QuqM+7og==, figureFileBig=X1N8usSL3uyBPFUcsXx0Hw==, tableContent=null), ArticleFig(id=1261377071272608573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图5, caption=空间位置距离聚类结果, figureFileSmall=0mT6bLNBxCEY+9QuqM+7og==, figureFileBig=X1N8usSL3uyBPFUcsXx0Hw==, tableContent=null), ArticleFig(id=1261377071780119362, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.6, caption=Hydrogeological attribute clustering results, figureFileSmall=g/3RW+LXl/1t8K7Bvo0tGA==, figureFileBig=QIJDy9nGyV0GsXdWZ63jcQ==, tableContent=null), ArticleFig(id=1261377072010806089, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图6, caption=水文地质属性聚类结果, figureFileSmall=g/3RW+LXl/1t8K7Bvo0tGA==, figureFileBig=QIJDy9nGyV0GsXdWZ63jcQ==, tableContent=null), ArticleFig(id=1261377072186966860, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.7, caption=Mixed clustering results, figureFileSmall=KbsI2IeSY1aeQkVOSBboRQ==, figureFileBig=MXZV2wlI86F+Y4qsDMB4ng==, tableContent=null), ArticleFig(id=1261377073990517591, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图7, caption=混合聚类结果, figureFileSmall=KbsI2IeSY1aeQkVOSBboRQ==, figureFileBig=MXZV2wlI86F+Y4qsDMB4ng==, tableContent=null), ArticleFig(id=1261377074321867612, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.8, caption=Thematic map of connectivity of karst aquifer observation wells, figureFileSmall=63xN2mk7ohZX5KvoQNVp1A==, figureFileBig=Ceez+t64uT/uwGZzTgcWEQ==, tableContent=null), ArticleFig(id=1261377074661606245, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图8, caption=岩溶含水层观测井连通性专题图, figureFileSmall=63xN2mk7ohZX5KvoQNVp1A==, figureFileBig=Ceez+t64uT/uwGZzTgcWEQ==, tableContent=null), ArticleFig(id=1261377074942624622, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.9, caption=Diagram of the internal structure of the LSTM, figureFileSmall=QIEUPHVY7wfrEUnf+XGIPA==, figureFileBig=V5bfGKBDEtifrH1miP1ebw==, tableContent=null), ArticleFig(id=1261377075156534135, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图9, caption=LSTM内部结构图

ft为遗忘门;it为输入门;${\tilde{c}}_{t}$为候选记忆细胞;ot为输出门;$\sigma $为非线性激活函数;tanh为激活函数;ct-1为长时记忆输入;ct为长时记忆输出;xt为输入;ht-1为隐藏层输入;ht为输出

, figureFileSmall=QIEUPHVY7wfrEUnf+XGIPA==, figureFileBig=V5bfGKBDEtifrH1miP1ebw==, tableContent=null), ArticleFig(id=1261377075341083518, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.10, caption=ConvLSTM internals structure, figureFileSmall=UWsx6+vm4yERg+rz9uC+JA==, figureFileBig=jrsa/NFLi320fLTTQVuVLQ==, tableContent=null), ArticleFig(id=1261377075567575944, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图10, caption=ConvLSTM内部结构, figureFileSmall=UWsx6+vm4yERg+rz9uC+JA==, figureFileBig=jrsa/NFLi320fLTTQVuVLQ==, tableContent=null), ArticleFig(id=1261377075970229139, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.11, caption=Schematic diagram of the ConvLSTM model, figureFileSmall=fqzVMa+Kh2o3xYutw+IfXg==, figureFileBig=ZS4gngRtrpXs/widbIaC1w==, tableContent=null), ArticleFig(id=1261377076184138647, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图11, caption=ConvLSTM模型示意图

Xst为空间信息输入数据;Gst为空间信息候选细胞;Hst为空间信息输出;Hat为注意力加权后的输出;CNN为卷积层;LSTM Network为长短期记忆网络;Attention Model为注意力机制

, figureFileSmall=fqzVMa+Kh2o3xYutw+IfXg==, figureFileBig=ZS4gngRtrpXs/widbIaC1w==, tableContent=null), ArticleFig(id=1261377076431602591, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.12, caption=RMSE of the predicted groundwater level results obtained from 16 wells in four models, figureFileSmall=hmmdY6OAGLFpKJlvu9Bv4w==, figureFileBig=ttTZ+Nv5SgRGI8shxkmPbw==, tableContent=null), ArticleFig(id=1261377076570014630, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图12, caption=4种模型中16口井得到的地下水位预测结果的RMSE, figureFileSmall=hmmdY6OAGLFpKJlvu9Bv4w==, figureFileBig=ttTZ+Nv5SgRGI8shxkmPbw==, tableContent=null), ArticleFig(id=1261377076733592493, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Fig.13, caption=Simulation results of some of the wells in the four models, figureFileSmall=w4GHQlNgrkyUP89zna7Urg==, figureFileBig=DiAKE7vnPYsgHBT2eCQV9w==, tableContent=null), ArticleFig(id=1261377078470034355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=图13, caption=4个模型中部分井的模拟预测结果, figureFileSmall=w4GHQlNgrkyUP89zna7Urg==, figureFileBig=DiAKE7vnPYsgHBT2eCQV9w==, tableContent=null), ArticleFig(id=1261377078742664121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Table 1, caption=

Observation well location and hydrogeological properties

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 X Y 水位埋深/m 水位方差/m 单井涌水量/(m3·d-1) 起伏度/m 坡度/(°) 离断层距离/m
No.1 117.12 36.63 38.47 179.02 500 70 4.55 3 502.63
No.2 117.01 36.54 37.44 2.99 500 34 3.43 5 943.78
No.3 116.91 36.59 26.95 3.53 2 500 39 1.18 4 031.99
No.4 117.21 36.72 29.73 1.14 2 500 31 2.56 838.63
No.5 116.71 36.56 1.47 1.08 7 500 22 7.34 160.50
No.6 116.78 36.60 5.99 1.37 7 500 21 1.97 1 558.72
No.7 116.71 36.57 11.67 1.39 7 500 26 3.43 427.73
No.8 116.84 36.65 3.20 0.98 7 500 23 3.71 3 654.12
No.9 116.86 36.62 12.76 1.00 7 500 22 0.66 895.40
No.10 116.87 36.59 22.97 3.53 7 500 43 6.29 208.02
No.11 117.01 36.66 8.67 0.24 7 500 44 1.18 912.59
No.12 117.03 36.66 22.55 0.28 7 500 31 3.03 1 751.44
No.13 117.17 36.70 23.61 1.93 2 500 22 1.86 2 441.75
No.14 117.14 36.73 0.82 0.44 2 500 26 6.87 1 465.39
No.15 117.01 36.67 13.75 0 2 500 25 12.86 1 526.24
No.16 117.02 36.67 6.74 0 2 500 23 3.84 1 926.57
), ArticleFig(id=1261377078998516671, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=表1, caption=

观测井位置和水文地质属

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 X Y 水位埋深/m 水位方差/m 单井涌水量/(m3·d-1) 起伏度/m 坡度/(°) 离断层距离/m
No.1 117.12 36.63 38.47 179.02 500 70 4.55 3 502.63
No.2 117.01 36.54 37.44 2.99 500 34 3.43 5 943.78
No.3 116.91 36.59 26.95 3.53 2 500 39 1.18 4 031.99
No.4 117.21 36.72 29.73 1.14 2 500 31 2.56 838.63
No.5 116.71 36.56 1.47 1.08 7 500 22 7.34 160.50
No.6 116.78 36.60 5.99 1.37 7 500 21 1.97 1 558.72
No.7 116.71 36.57 11.67 1.39 7 500 26 3.43 427.73
No.8 116.84 36.65 3.20 0.98 7 500 23 3.71 3 654.12
No.9 116.86 36.62 12.76 1.00 7 500 22 0.66 895.40
No.10 116.87 36.59 22.97 3.53 7 500 43 6.29 208.02
No.11 117.01 36.66 8.67 0.24 7 500 44 1.18 912.59
No.12 117.03 36.66 22.55 0.28 7 500 31 3.03 1 751.44
No.13 117.17 36.70 23.61 1.93 2 500 22 1.86 2 441.75
No.14 117.14 36.73 0.82 0.44 2 500 26 6.87 1 465.39
No.15 117.01 36.67 13.75 0 2 500 25 12.86 1 526.24
No.16 117.02 36.67 6.74 0 2 500 23 3.84 1 926.57
), ArticleFig(id=1261377079166288839, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Table 2, caption=

Mixed clustering results of observation wells

, figureFileSmall=null, figureFileBig=null, tableContent=
类1 类2 类3 类4 类5 类6 类7
No.5 No.4 No.2 No.15 No.11 No.1 No.10
No.6 No.13 No.3 No.16 No.12
No.7 No.14
No.8
No.9
), ArticleFig(id=1261377079443112907, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=表2, caption=

观测井混合聚类结果

, figureFileSmall=null, figureFileBig=null, tableContent=
类1 类2 类3 类4 类5 类6 类7
No.5 No.4 No.2 No.15 No.11 No.1 No.10
No.6 No.13 No.3 No.16 No.12
No.7 No.14
No.8
No.9
), ArticleFig(id=1261377079703159761, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Table 3, caption=

Influencing factors of groundwater level

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 指标 影响过程
降雨 降水入渗补给使水位上升
河流水位 地下水动态受地表水的明显影响。河水位上升时,近岸处的水位上升最快,上升幅度最大;远离河岸,水位变化幅度变小,反应时间滞后
自然因素 气温 气温影响地下水的蒸发速度,气温越高,蒸发越快
蒸散发 地下水受温度等因素蒸散发
地质条件 地质因素影响地下水位的变化幅度与变化速度。例如,承压含水层受到上覆隔水层的限制,补给区动态变化强烈而迅速,远离补给区则变得微弱而滞后
人为因素 地下水开
采或补给
人为的开采或补给地下水,导致地下水位短时间内急剧下降或上升
地表水漫灌 地表水大水漫灌而不加强排水,导致灌水入渗,水位上升
), ArticleFig(id=1261377079942235094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=表3, caption=

地下水位影响因素

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 指标 影响过程
降雨 降水入渗补给使水位上升
河流水位 地下水动态受地表水的明显影响。河水位上升时,近岸处的水位上升最快,上升幅度最大;远离河岸,水位变化幅度变小,反应时间滞后
自然因素 气温 气温影响地下水的蒸发速度,气温越高,蒸发越快
蒸散发 地下水受温度等因素蒸散发
地质条件 地质因素影响地下水位的变化幅度与变化速度。例如,承压含水层受到上覆隔水层的限制,补给区动态变化强烈而迅速,远离补给区则变得微弱而滞后
人为因素 地下水开
采或补给
人为的开采或补给地下水,导致地下水位短时间内急剧下降或上升
地表水漫灌 地表水大水漫灌而不加强排水,导致灌水入渗,水位上升
), ArticleFig(id=1261377080416191447, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Table 4, caption=

Model data set partition

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集类型 数量 比例
训练集 3 456 75%
验证集 每批次中训练集的20%
预测集 1 152 25%
), ArticleFig(id=1261377080806261727, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=表4, caption=

模型数据集划分

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集类型 数量 比例
训练集 3 456 75%
验证集 每批次中训练集的20%
预测集 1 152 25%
), ArticleFig(id=1261377081024365539, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Table 5, caption=

Input variables and model parameters of the fourmodels

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 输入变量 卷积
核大
隐藏层
神经元
个数
学习
验证
误差
SV-LSTM GWL、GW${{\mathrm{L}}_{t}}_{-1}$ 8 0.003 0.023 6
MV-LSTM GWL、R、GW${{\mathrm{L}}_{t}}_{-1}$
${{R}_{t}}_{-1}$
6 0.003 0.013 8
D-MV-ConvLSTM GWL、R、GW${{\mathrm{L}}_{t}}_{-1}$
${{R}_{t}}_{-1}$、GWLd
5 7 0.003 0.011 1
M-MV-ConvLSTM GWL、R、GW${{\mathrm{L}}_{t}}_{-1}$
${{R}_{t}}_{-1}$、GWLc
5 5 0.005 0.010 0
), ArticleFig(id=1261377081313772522, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=表5, caption=

4个模型的输入变量和模型参数

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 输入变量 卷积
核大
隐藏层
神经元
个数
学习
验证
误差
SV-LSTM GWL、GW${{\mathrm{L}}_{t}}_{-1}$ 8 0.003 0.023 6
MV-LSTM GWL、R、GW${{\mathrm{L}}_{t}}_{-1}$
${{R}_{t}}_{-1}$
6 0.003 0.013 8
D-MV-ConvLSTM GWL、R、GW${{\mathrm{L}}_{t}}_{-1}$
${{R}_{t}}_{-1}$、GWLd
5 7 0.003 0.011 1
M-MV-ConvLSTM GWL、R、GW${{\mathrm{L}}_{t}}_{-1}$
${{R}_{t}}_{-1}$、GWLc
5 5 0.005 0.010 0
), ArticleFig(id=1261377083243152367, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=EN, label=Table 6, caption=

RMSE and NSE of groundwater level prediction results obtained from 16 wells in the four models

, figureFileSmall=null, figureFileBig=null, tableContent=
观测井编号 SV-LSTM MV-LSTM D-MV-ConvLSTM M-MV-ConvLSTM
RMSE NSE RMSE NSE RMSE NSE RMSE NSE
No.1 9.192 -0.146 4.836 0.677 3.518 0.832 2.954 0.881
No.2 5.012 -24.152 2.339 -1.063 0.770 0.406 0.935 0.124
No.3 0.507 0.854 0.259 0.895 0.373 0.921 0.257 0.962
No.4 1.129 -0.212 0.915 0.056 0.916 0.202 0.960 0.122
No.5 0.342 0.807 0.313 0.768 0.315 0.836 0.261 0.888
No.6 0.285 0.845 0.269 0.784 0.263 0.867 0.217 0.910
No.7 0.367 0.766 0.284 0.774 0.295 0.848 0.221 0.916
No.8 0.262 0.746 0.208 0.686 0.216 0.827 0.174 0.888
No.9 0.387 0.927 0.218 0.939 0.214 0.978 0.112 0.994
No.10 0.550 0.798 0.401 0.837 0.456 0.861 0.358 0.914
No.11 0.341 0.075 0.181 0.502 0.155 0.809 0.088 0.939
No.12 0.346 0.144 0.187 0.545 0.162 0.813 0.094 0.937
No.13 0.707 0.670 0.556 0.813 0.567 0.788 0.428 0.879
No.14 0.786 -0.765 0.283 0.508 0.218 0.864 0.155 0.931
No.15 1.055 -498.447 0.504 -8.943 0.274 -32.608 0.032 0.540
No.16 0.792 -1 261.636 0.176 -331.881 0.230 -105.330 0.068 -8.361
平均值 1.379 -111.171 0.746 -20.819 0.559 -7.943 0.457 0.216
), ArticleFig(id=1261377083494810609, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1261262693164527968, language=CN, label=表6, caption=

4种模型中16口井得到的地下水位预测结果的RMSE和NSE

, figureFileSmall=null, figureFileBig=null, tableContent=
观测井编号 SV-LSTM MV-LSTM D-MV-ConvLSTM M-MV-ConvLSTM
RMSE NSE RMSE NSE RMSE NSE RMSE NSE
No.1 9.192 -0.146 4.836 0.677 3.518 0.832 2.954 0.881
No.2 5.012 -24.152 2.339 -1.063 0.770 0.406 0.935 0.124
No.3 0.507 0.854 0.259 0.895 0.373 0.921 0.257 0.962
No.4 1.129 -0.212 0.915 0.056 0.916 0.202 0.960 0.122
No.5 0.342 0.807 0.313 0.768 0.315 0.836 0.261 0.888
No.6 0.285 0.845 0.269 0.784 0.263 0.867 0.217 0.910
No.7 0.367 0.766 0.284 0.774 0.295 0.848 0.221 0.916
No.8 0.262 0.746 0.208 0.686 0.216 0.827 0.174 0.888
No.9 0.387 0.927 0.218 0.939 0.214 0.978 0.112 0.994
No.10 0.550 0.798 0.401 0.837 0.456 0.861 0.358 0.914
No.11 0.341 0.075 0.181 0.502 0.155 0.809 0.088 0.939
No.12 0.346 0.144 0.187 0.545 0.162 0.813 0.094 0.937
No.13 0.707 0.670 0.556 0.813 0.567 0.788 0.428 0.879
No.14 0.786 -0.765 0.283 0.508 0.218 0.864 0.155 0.931
No.15 1.055 -498.447 0.504 -8.943 0.274 -32.608 0.032 0.540
No.16 0.792 -1 261.636 0.176 -331.881 0.230 -105.330 0.068 -8.361
平均值 1.379 -111.171 0.746 -20.819 0.559 -7.943 0.457 0.216
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405660, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405660, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405660, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405660, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于距离-属性混合聚类结合ConvLSTM模型的岩溶地层地下水预测方法
收藏切换
PDF下载
高明 1 , 李虎 2, * , 刘鑫锦 2 , 张康 2 , 韩健勇 1
科学技术与工程 | 论文·天文学、地球科学 2025,25(20): 8424-8434
收起
收藏切换
科学技术与工程 | 论文·天文学、地球科学 2025, 25(20): 8424-8434
基于距离-属性混合聚类结合ConvLSTM模型的岩溶地层地下水预测方法
全屏
高明1 , 李虎2, * , 刘鑫锦2, 张康2, 韩健勇1
作者信息
  • 1 山东建筑大学土木工程学院, 济南 250101
  • 2 济南轨道交通集团有限公司, 济南 250014
  • 高明(1998—),男,汉族,山东临沂人,硕士研究生。研究方向:隧道工程。E-mail:

通讯作者:

* 李虎(1983—),男,汉族,山东济南人,博士,高级工程师。研究方向:轨道交通工程建设。E-mail:
Prediction Method of Groundwater in Karst Strata Based on Distance-attribute Hybrid Clustering Combined with ConvLSTM Model
Ming GAO1 , Hu LI2, * , Xin-jin LIU2, Kang ZHANG2, Jian-yong HAN1
Affiliations
  • 1 School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China
  • 2 Jinan Rail Transit Group Co., Ltd., Jinan 250014, China
出版时间: 2025-07-18 doi: 10.12404/j.issn.1671-1815.2405660
文章导航
收藏切换

为解决因地下水相关因素未考虑充分而导致的模型对地下水位预测不准确的问题,提出观测井的空间位置距离聚类方法、水文地质属性聚类方法和距离-属性混合聚类方法,验证观测井间连通性在地下水位预测中的重要性。设计4种模型并分别对济南岩溶水域的地下水位进行模拟和预测并与实际观测值对比。预测结果表明:考虑岩溶含水层连通性特征的联合模型ConvLSTM(convolution-long short term memory)要优于传统的长短期记忆网络模型(long short term memory,LSTM)。其中考虑距离-属性混合聚类结果的同类别井(连通性强)的模型(mix-multivariate-convolution-long short term memory,M-MV-ConvLSTM)预测结果精度最高、误差最小,其平均均方根误差约为0.457,纳什效率系数约为0.216,预测准确度高于传统的LSTM预测模型。研究成果可为岩溶水域的实时地下水位预测提供借鉴。

地下水位预测  /  长短期记忆网络(LSTM)  /  聚类  /  岩溶含水层

To address the issue of inaccuracies in groundwater level predictions due to the insufficient consideration of groundwater-related factors, clustering methods for observation wells based on spatial distance, hydrogeological attributes, and a hybrid of distance and attributes were proposed. The significance of inter-well connectivity in groundwater level prediction was validated. Four models were designed, which were applied to simulate and predict groundwater levels in the karst water region of Jinan and compared with actual observations. The prediction results indicate that the combined model incorporating the connectivity characteristics of karst aquifers, known as convolution-long short-term memory(ConvLSTM), outperforms the traditional long short-term memory(LSTM) model. Among the models, the mix-multivariate-convolution-long short-term memory(M-MV-ConvLSTM) model, which accounts for wells of the same category based on the hybrid distance-attribute clustering results (characterized by strong connectivity), achieves the highest prediction accuracy and the smallest error. The average root mean square error is approximately 0.457, and the Nash-Sutcliffe efficiency is approximately 0.216, demonstrating a higher prediction accuracy than the traditional LSTM model. The research results is positioned to serve as a reference for real-time groundwater level prediction in karst regions.

groundwater level prediction  /  long short term memory network(LSTM)  /  cluster  /  karst aquifer
高明, 李虎, 刘鑫锦, 张康, 韩健勇. 基于距离-属性混合聚类结合ConvLSTM模型的岩溶地层地下水预测方法. 科学技术与工程, 2025 , 25 (20) : 8424 -8434 . DOI: 10.12404/j.issn.1671-1815.2405660
Ming GAO, Hu LI, Xin-jin LIU, Kang ZHANG, Jian-yong HAN. Prediction Method of Groundwater in Karst Strata Based on Distance-attribute Hybrid Clustering Combined with ConvLSTM Model[J]. Science Technology and Engineering, 2025 , 25 (20) : 8424 -8434 . DOI: 10.12404/j.issn.1671-1815.2405660
一直以来地下水都与人们有着密不可分的联系,不管是对地下水的合理开发与可持续利用,还是由于水位变化引起的城市内涝等灾害,均体现了地下水对人类生活的重要影响。目前,学者们主要关注对地下水位实时监测的研究,忽略了地下水位预测的重要性。不同位置地下水位之间存在着联系,但由于不同地质条件与周边环境造成地下水位间的关系十分复杂,通常不能有效准确地对地下水位预测。
近年来,深度学习技术不断革新发展。其中长短期记忆网络模型(long short term memory,LSTM)模型[1-4]适用于处理和预测时间序列中间隔和延迟非常长的重要事件,并且解决了循环神经网络(recurrent neural network,RNN)存在的梯度消失和爆炸问题[5-6]。因此,诸多学者基于LSTM模型对地下水位预测展开研究。闫佰忠等[7]为解决以往模型未考虑地下水位相关影响因素的问题,探讨LSTM在地下水位预测中的应用,利用LSTM模型,采用多变量输入的方式,构建了基于多变量LSTM的地下水水位预测模型。汪云等[8]利用LSTM构建地下水水位预测模型,解决了传统神经网络预测模型处理时序数据时未考虑时间序列的问题,同时采用多影响变量输入的方式弥补了简单时序模型处理数据时过于依赖时间的缺点。冯希尧等[9]为解决未考虑最优因子组合,会对地下水潜在性制图产生不利影响等问题,提出了遗传算法优化支持向量机的地下水潜在性预测方法,优化后模型的准确度为0.777,验证集(area under curve,AUC)为0.806,结果表明,遗传算法优化的支持向量机模型的预测准确度高、可靠性好。胡飞跃等[10]构建了滑动窗口-长短期记忆神经网络模型(sliding window algorithm-long short term memory,SWA-LSTM),利用地下水位变化于降雨量的滞后性关系对地下水位进行预测,弥补了简单LSTM模型过度依赖周期性规律而忽视降雨量对地下水位变化规律的影响的缺点。侯金霄等[11]针对岩溶地下水水位预测精度较差的问题,提出一种(empirical mode decomposition-long short term memory,EMD-LSTM)耦合模型,具有较强的可靠性和稳定性,可为岩溶地下水水位的精确预测提供借鉴。郭艺等[12]运用时间序列分析方法分析了济南市区岩溶泉水位动态变化规律,建立的泉水位预测模型可以较好地预测该地区岩溶泉水位。
针对地下水位的预测,传统的神经网络模型已无法满足对预测准确度需求。鉴于此,把卷积神经网络(convolutional neural network,CNN)[13-15]和LSTM网络相结合构成ConvLSTM模型,其不仅具有LSTM的时间建模能力,而且还可以描绘局部特征,并利用K-means聚类算法对观测点的空间位置和水文地质属性聚类,聚类结果可用于岩溶含水层连通性分析,在地下结构复杂多变的岩溶地层,聚类结果与模型结合以期获得合理有效的预测结果。
岩溶含水层水量丰富而不均一,不同观测井间因水流特征可能会有连通关系,若忽视观测井之间的连通性,预测结果准确性将会下降。对观测井间的连通性分析有效避免了模型对地下水位预测的不准确不精确问题。选取山东省济南市马山断裂与港沟断裂之间的碳酸盐岩岩溶含水层区域。研究区范围和观测井的位置如图1所示。
岩溶含水层连通性分析主要包括观测井基本信息、断层断裂、地下水位监测序列和数字高程模型(digital elevation model,DEM)数据,提取各观测井坐标和水文地质因子按特征聚类后得出聚类结果。按条件结合两类结果最后进行连通性分析得出含水层连通性专题图,连通性分析总流程图如图2所示。
数据源包括该区域内布设的16 口观测井及其长期地下水位监测序列、30 m分辨率DEM数据如图3所示。
读取和计算16口观测井的坐标位置、地下水埋深、水位方差、离断层距离,以及观测井处的地形起伏度、坡度等聚类变量,并分别存入观测井位置集合和水文地质属性集合,可分别表示为
${W}_{\mathrm{e}\mathrm{l}\mathrm{l}\mathrm{p}}=\left\{{w}_{\mathrm{p}i}\right({x}_{i},{y}_{i}\left)\right|i=\mathrm{0,1},\dots,{n}_{\mathrm{w}}\}$
${W}_{\mathrm{H}\mathrm{y}\mathrm{d}\mathrm{r}\mathrm{o}}=\left\{{w}_{\mathrm{h}\mathrm{d}i}\right({g}_{\mathrm{d}i},{g}_{\mathrm{v}i},{w}_{\mathrm{y}\mathrm{d}i},{w}_{\mathrm{t}\mathrm{r}i},{w}_{\mathrm{s}i},{w}_{\mathrm{f}i}\left)\right|i=\mathrm{1,2},\dots,{n}_{\mathrm{w}}\}$
式中:xi为观测井的横坐标;yi为观测井的纵坐标;wpi为观测井的位置属性集;nw为观测井数量,whdi为观测井的水文地质属性集;gdi为地下水埋深因子;gvi为地下水位方差因子;wydi为单井涌水量因子;wtri为地形起伏度值;wsi为坡度因子,wfi为离断层距离因子。
选取聚类变量的步骤如下。
步骤1 创建观测井集合。
${W}_{\mathrm{e}\mathrm{l}\mathrm{l}}=\left\{{w}_{i}\right({w}_{\mathrm{p}i},{w}_{\mathrm{h}\mathrm{d}i}\left)\right|i=\mathrm{1,2},\dots,{n}_{\mathrm{w}}\}$
步骤2 读取观测井基本信息表中观测井的编号、坐标位置,得到观测井位置属性集合。
${W}_{\mathrm{e}\mathrm{l}\mathrm{l}\mathrm{p}}=\left\{{w}_{\mathrm{p}i}\right({x}_{i},{y}_{i}\left)\right|i=\mathrm{1,2},\dots,{n}_{\mathrm{w}}\}$
步骤3 读取观测井的长期地下水位监测时间序列数据,获取和计算观测井的地下水埋深因子gdi,地下水位方差因子gvi
步骤4 读取由抽水试验获得的观测井的单井涌水量因子wydi
步骤5 读取DEM数据,计算观测井所处位置的地形起伏度值wtri
步骤6 计算观测井所处位置的坡度值,得到坡度因子wsi
步骤7 读取断裂数据文件,计算观测井距最近的断裂的距离,得到离断层距离因子wfi
步骤8 循环执行步骤3~7,得到所有观测井的水文地质属性信息,并存入集合${W}_{\mathrm{H}\mathrm{y}\mathrm{d}\mathrm{r}\mathrm{o}}$中。
基于${W}_{\mathrm{e}\mathrm{l}\mathrm{l}\mathrm{p}}、{W}_{\mathrm{H}\mathrm{y}\mathrm{d}\mathrm{r}\mathrm{o}},$更新观测井集合,可表示为
${W}_{\mathrm{e}\mathrm{l}\mathrm{l}}=\left\{{w}_{i}\right({w}_{\mathrm{p}i},{w}_{\mathrm{h}\mathrm{d}i}\left)\right|i=\mathrm{1,2},\dots,{n}_{\mathrm{w}}\}$
得到更新后的观测井数据如表1所示。
为了消除指标之间的量纲影响,需要进行数据标准化处理,以解决数据指标之间的可比性。原始数据经过数据标准化处理后,各指标处于同一数量级,适合进行综合对比评价。
对观测井的水文地质属性集合${W}_{\mathrm{H}\mathrm{y}\mathrm{d}\mathrm{r}\mathrm{o}}$中的各个因子,分别进行Z-Score标准化处理,得到标准化处理后的集合${W}_{\mathrm{H}\mathrm{y}\mathrm{d}\mathrm{r}\mathrm{o}}。$
基于空间位置因子和水文地质因子中所提供的数据,通过利用K-means聚类算法[16-18]对数据进行计算分类从而得到相应的聚类结果。聚类方法流程图如图4所示。
空间位置距离聚类由K-means聚类算法分类得出,它基于距离要求把符合要求的相应观测井分到一种类别组中[19],此分类对后文地下水位预测中起到关键作用。空间位置距离聚类流程如图4所示。具体聚类方法如下。
读取观测井位置属集合${W}_{\mathrm{e}\mathrm{l}\mathrm{l}\mathrm{P}},$${W}_{\mathrm{e}\mathrm{l}\mathrm{l}\mathrm{P}}$中随机选取k个观测井作为距离聚类初始中心集合,可表示为
${D}_{\mathrm{C}\mathrm{P}}=\left\{{d}_{\mathrm{c}\mathrm{p}j}\right({d}_{\mathrm{c}\mathrm{p}xj},{d}_{\mathrm{c}\mathrm{p}yj}\left)\right|j=\mathrm{1,2},\dots,k\}$
并创建距离聚类分组集合:
DC={discatj(${w}_{j}^{m}$)|j=1,2,…,k;m=1,2,…,nj}
式中:dcpj为距离聚类中心点;dcpxj为横坐标;dcpyj为纵坐标;${d}_{\mathrm{i}\mathrm{s}\mathrm{c}\mathrm{a}\mathrm{t}j}$为距离聚类的第j个分组;${w}_{j}^{m}$为第j个分组中的第m个观测井;k为分组数;nj为第j个分组中观测井的数目。
开始K-means空间位置距离聚类,读取距离聚类中心点集合,即
${D}_{\mathrm{C}\mathrm{P}}=\left\{{d}_{\mathrm{c}\mathrm{p}j}\right({d}_{\mathrm{c}\mathrm{p}xj},{d}_{\mathrm{c}\mathrm{p}yj}\left)\right|j=\mathrm{1,2},\dots,k\}$
根据式(8)计算观测井wi与聚类中心dcpj的欧式距离,计算公式为
${d}_{ij}({w}_{i},{d}_{\mathrm{c}\mathrm{p}j})=\sqrt{({w}_{xi}-{d}_{\mathrm{c}\mathrm{p}xj}{)}^{2}+({w}_{yi}-{d}_{\mathrm{c}\mathrm{p}yj}{)}^{2}}$
式(9)中:wxi为观测井横坐标;wyi为观测井纵坐标。
得到观测井wiDCP中所有聚类中心点的欧式距离,获取与观测井距离最小的聚类中心点编号j,将观测井存入${d}_{\mathrm{i}\mathrm{s}\mathrm{c}\mathrm{a}\mathrm{t}j}。$重复上述操作,将所有的观测井都分类到距其最近的聚类中心点簇。
更新聚类中心,计算${d}_{\mathrm{i}\mathrm{s}\mathrm{c}\mathrm{a}\mathrm{t}j}$中包含的所有观测井的质心,将其作为新的聚类中心点,添加至新聚类中心点集合,即

NDCP={ndcpj(ndcpxj,ndcpyj)|j=1,2,…,k}

完成所有分组的中心点更新。并判断更新后的聚类中心点集合${N}_{\mathrm{D}\mathrm{C}\mathrm{P}}$相比原聚类中心集DCP是否发生改变,如果两集合相比发生变化,则将更新后的新聚类中心点集${N}_{\mathrm{D}\mathrm{C}\mathrm{P}}$赋值给DCP继续利用K-means聚类;如果未发生变化,则聚类结束,得到观测井的空间距离聚类结果如图5所示。
水文地质属性聚类流程如图4所示。水文地质属性聚类与空间位置距离聚类的聚类方法是一样的,其不同之处在于其属性聚类分为5个组,且水文地质属性的距离表达式变化为
$\begin{array}{l}{h}_{\mathrm{y}\mathrm{d}ij}({w}_{i},{h}_{\mathrm{c}\mathrm{p}i})=\left[\right({g}_{\mathrm{d}i}-{g}_{\mathrm{d}j}{)}^{2}+({g}_{\mathrm{v}i}-{g}_{\mathrm{v}j}{)}^{2}+\\ ({w}_{\mathrm{y}\mathrm{d}i}-{w}_{\mathrm{y}\mathrm{d}j}{)}^{2}+({w}_{\mathrm{t}\mathrm{r}i}-{w}_{\mathrm{t}\mathrm{r}j}{)}^{2}+\\ ({w}_{\mathrm{s}i}-{w}_{\mathrm{s}j}{)}^{2}+({w}_{\mathrm{f}i}-{w}_{\mathrm{f}j}{)}^{2}{]}^{\frac{1}{2}}\end{array}$
水文地质属性聚类结果如图6所示。
基于上述得到的空间距离聚类结果和水文地质属性聚类结果,采用交叉合并规则进行聚类结果的综合,得到混合聚类结果。混合聚类规则如下。
规则1 wiwj属于空间位置距离聚类DC中的同一组。
规则2 wiwj属于水文地质属性聚类HC中的同一组。
任意两个观测井wi${w}_{j}(i,j=\mathrm{1,2},\dots,{n}_{w};i\ne j),$如不符合规则1,则认为观测井wiwj之间不连通并将其分为不同类;如符合规则1而不符合规则2,则认为观测井wiwj间存在弱连通性并将其分为不同类;如同时符合规则1和规则2,则认为观测井wiwj之间存在强连通性并将其分为同一类满足规则后得出混合聚类结果MC,同一类的观测井之间为强连通,不同类之间的观测井为不连通或弱连通。混合聚类结果如图7所示。
进行聚类结果的效果评价,分组有效性通过 Calinski-Harabasz 伪 F 统计量(简称CH指标)来测量,是反映组内相似性和组间差异性的比率。依据式(12)~式(15)来计算CH的指标。
$\mathrm{C}\mathrm{H}=\frac{\frac{{R}^{2}}{k-1}}{\frac{1-{R}^{2}}{{n}_{\mathrm{w}}-k}}$
${R}^{2}=\frac{\mathrm{S}\mathrm{S}\mathrm{T}-\mathrm{S}\mathrm{S}\mathrm{E}}{\mathrm{S}\mathrm{S}\mathrm{T}}$
$SST=\stackrel{k}{\sum _{j=1}}\stackrel{{n}_{j}}{\sum _{i=1}}\stackrel{{n}_{v}}{\sum _{v=1}}({w}_{ji}^{v}-{\stackrel{-}{w}}^{v}{)}^{2}$
$SSE=\stackrel{k}{\sum _{j=1}}\stackrel{{n}_{j}}{\sum _{i=1}}\stackrel{{n}_{v}}{\sum _{v=1}}({w}_{ji}^{v}-{\stackrel{-}{w}}_{j}^{v}{)}^{2}$
式中:R2为决定系数;SST反映组间差别;SSE反映组内相似性;nw为观测井数目;nj为组j中的观测井数目;k为类(组)数目;nv为用于将观测井进行分组的变量数目;${w}_{ji}^{v}$为第j组中第i个观测井的第v个变量值;${\stackrel{-}{w}}^{v}$为所有观测井第v个变量值的平均值;${\stackrel{-}{w}}_{j}^{v}$为第j组中第v个变量值的平均值。
使用计算完成的CH指标值对聚类效果进行评估,该值越大表示聚类效果越好,用于评估不同聚类分组数目情况下的聚类效果。经过聚类效果评价,当距离聚类分为3组、属性聚类分为5组、综合后的混合聚类为7组时,混合聚类效果最佳,观测井的最终分组如表2所示。
在空间位置距离的聚类结果中(图5),观测井被分为三类,平均轮廓系数值最大。水文地质特征的聚类结果(图6),与图5相比有部分差异;如距离聚类结果中的11号、12号、15号、16号,由于这4口观测井的实际距离较近,感觉上会被归为同一类。但在基于水文地质特征的聚类结果中,它们的单井产水量和地下水位差异较大,因此分为两类。
混合聚类方法有效避免了两种错误:一是避免只考虑井距,而忽略观测井是否真正连通;二是避免了仅考虑观测井的水文地质特征时,聚类结果在空间上没有聚类的现象。
岩溶含水层连通性的强弱会影响到模型的精度与准确性,因此需要对连通性进行强弱的划分。基于观测井点状数据构建不规则三角网;基于混合聚类结果,观测井之间不连通、弱连通和强连通关系分别使用不同类型的直线符号进行表示,制作观测井连通性专题图如图8所示。
地下水位的动态变化受到自然因素和人为因素影响,影响过程如表3所示。现有的地下水位预测研究表明,使用人工智能模型来预测地下水位时,地下水位时间序列的过去步长和降水是最常用的变量输入。根据研究区的实际情况和数据可用性,本研究采用套索回归方法,基于回归权重从原始数据中提取重要变量[20]
结合岩溶含水层连通性分析结果,考虑到岩溶含水层的水流特征与其空间连通性密切相关,在预测目标井的地下水位时,还需要考虑到与其连通性较好的其他观测井对其影响程度。因此,最终选择的输入变量是地下水位、地下水位时间序列的过去步长、降雨量、降雨量序列的过去步长和同类别井(相互间具有强连通性)的地下水位序列。
在使用神经网络模型进行预测前,需要将输入的数据集进行转化。预测井的地下水位和相关变量用一维向量表示为
$w=({G}_{\mathrm{p}},{R}_{\mathrm{p}},{G}_{\mathrm{c}\mathrm{a}\mathrm{t}})$
式(16)中:Gp为目标预测井的地下水位;Rp为降雨量;Gcat为与预测井属于同一类别的其余观测井的平均地下水位值。
运用式(17)将多个时间步长的一维向量组成一个二维矩阵,用于表示一段时间内的输入数据,即作为时间窗口。运用式(18)将该时间窗口从时间序列方向滑动预测井的完整数据序列,可以得到该预测井的多个时间窗数据。
$W=\left[\begin{array}{l}{w}_{1}\\ {w}_{2}\\ ︙\\ {w}_{m}\end{array}\right]=\left[\begin{array}{lll}{G}_{\mathrm{p}}^{1}& {R}_{\mathrm{p}}^{1}& {G}_{\mathrm{c}\mathrm{a}\mathrm{t}}^{1}\\ {G}_{\mathrm{p}}^{2}& {R}_{\mathrm{p}}^{2}& {G}_{\mathrm{c}\mathrm{a}\mathrm{t}}^{2}\\ ︙& ︙& ︙\\ {G}_{\mathrm{p}}^{m}& {R}_{\mathrm{p}}^{m}& {G}_{\mathrm{c}\mathrm{a}\mathrm{t}}^{m}\end{array}\right]$
${P}_{\mathrm{k}}=\left[\begin{array}{l}{W}_{1}^{k}\\ {W}_{2}^{k}\\ ︙\\ {W}_{n}^{k}\end{array}\right]=\left[\begin{array}{llll}{w}_{1}^{1}& {w}_{2}^{1}& \dots & {w}_{m}^{1}\\ {w}_{1}^{2}& {w}_{2}^{2}& \dots & {w}_{m}^{2}\\ ︙& ︙& \mathrm{ }& ︙\\ {w}_{1}^{n}& {w}_{2}^{n}& \dots & {w}_{m}^{n}\end{array}\right]$
式中:W为时间窗内的数据;m为时间窗的大小;${G}_{p}^{m},{R}_{\mathrm{p}}^{m}$${G}_{cat}^{m}$分别为时间窗内时刻m${G}_{\mathrm{p}}、{R}_{\mathrm{p}}$Gcat;Pk为目标预测井k的数据;${w}_{n}^{k}$为目标预测井k的时间窗n;${w}_{m}^{n}$为第n个时间窗口中m时间处的w
将16口观测井的数据整合到一个输入矩阵IPD中,进入ConvLSTM模型,见式(19)。该网络可以学习区域内观测井的地下水位共性特征,以单一的预测模型实现对区域内多个观测井的实时高效的地下水位预测效果。
${I}_{PD}=\left[\begin{array}{l}{P}_{1}\\ {P}_{2}\\ ︙\\ {P}_{16}\end{array}\right]=\left[\begin{array}{llll}{w}_{1}^{1}& {w}_{2}^{1}& \dots & {w}_{n}^{1}\\ {w}_{1}^{2}& {w}_{2}^{2}& \dots & {w}_{n}^{2}\\ ︙& ︙& \mathrm{ }& ︙\\ {w}_{1}^{16}& {w}_{2}^{16}& \dots & {w}_{n}^{16}\end{array}\right]$
在众多随机性模型中,神经网络模型由于具有大规模并行和分布式处理、自适应、自组织和自学习功能,以及良好的容错性和强大的自我调节能力等特点,被众多学者用以进行预测工作。并且人工神经网络有着适应于水文资源系统的独特优越性:人工神经网络可在事先不知道数据中潜在规律性的情况下从提供的实例中学习、总结数据中内在的规律性,并且调整自身行为以适应新信息或环境,从而具有从已有状态向新的环境状态进化的概括能力。
神经网络模型中,LSTM适用于处理和预测时间序列中间隔和延迟非常长的重要事件,并且解决了RNN存在的梯度消失和梯度爆炸问题。因此选用LSTM作为本实验的基本预测模型。
对于给定序列$x=({x}_{1},{x}_{2},\dots,{x}_{n}),$应用一个标准的RNN模型,可以通过迭代式(20)和式(21)计算出一个隐藏层序列$h=({h}_{1},{h}_{2},\dots,{h}_{n})$和一个输出序列$y=({y}_{1},{y}_{2},\dots,{y}_{n})。$
${h}_{t}={f}_{\mathrm{a}}({W}_{xh}{x}_{t}+{W}_{hh}{h}_{\mathrm{t}-1}+{b}_{n})$

yt=Whyht+by

式中:htt时刻的隐藏状态向量;xtt时刻的输入;ytt时刻的输出;WxhWhyWhh为权重系数矩阵;bn、by为偏置向量;fa为激活函数;下标t为时刻。
LSTM模型是将隐藏层的RNN细胞替换为LSTM细胞,使其具有长期记忆能力。经过不断地演化,目前应用最为广泛的LSTM模型细胞结构如图9所示。
虽然LSTM网络可以有效提取时间序列的时间特征,但网络无法捕捉数据的空间特征。ConvLSTM 模型包括卷积神经网络和LSTM网络,其不仅具有LSTM的时间建模能力,而且还可以描绘局部特征。该模型通过在多维数据中进行卷积运算来捕捉基本的空间特征,并用LSTM单元中每个门的卷积运算代替矩阵乘法步骤,提取数据的时空特征。本研究设计的ConvLSTM模型的内部结构如图10所示,其既具备LSTM网络的时间建模能力,同时具备CNN描绘数据的空间特征能力。
ConvLSTM计算过程见式(22)~式(26)。

it=σ(Wxi*Xt+Whi*Ht-1+WciCt-1+bi)

${f}_{t}=\sigma ({W}_{\mathrm{x}\mathrm{f}}\mathrm{*}{X}_{t}+{W}_{\mathrm{h}\mathrm{f}}\mathrm{*}{H}_{\mathrm{t}-1}+{W}_{\mathrm{c}\mathrm{f}}{C}_{\mathrm{t}-1}+{b}_{f})$

Ct=ftCt-1+ittanh(Wxc*Xt+Whc*Ht-1+bc)

${o}_{\mathrm{t}}=\sigma ({W}_{xo}\mathrm{*}{X}_{t}+{W}_{ho}\mathrm{*}{H}_{t-1}+{W}_{co}☉{C}_{\mathrm{t}}+{b}_{o})$
${H}_{\mathrm{t}}={o}_{t}☉\mathrm{t}\mathrm{a}\mathrm{n}\mathrm{h}\left({C}_{t}\right)$
式中:itftCtot分别为LSTM结构中的输入门、遗忘门、控制单元和输出门;σ为非线性激活函数;Xtt时刻的输入;Htt时刻的输出;${W}_{\mathrm{x}\mathrm{i}}、{W}_{hi}、{W}_{\mathrm{c}\mathrm{i}}、{W}_{\mathrm{x}\mathrm{f}}、{W}_{\mathrm{h}\mathrm{f}}、{W}_{\mathrm{c}\mathrm{f}}、{W}_{\mathrm{x}\mathrm{c}}、{W}_{\mathrm{h}\mathrm{c}}、{W}_{\mathrm{x}\mathrm{o}}、{W}_{\mathrm{h}\mathrm{o}}、{W}_{\mathrm{c}\mathrm{o}}$为权重矩阵参数;☉为Hadamard积符号;*为卷积运算符号;bibobfbc为偏置向量;tanh为激活函数。
本项目使用的 ConvLSTM 模型如图11所示。它由两个卷积层和两个LSTM层组成。
选取山东省济南市马山断裂与港沟断裂之间的碳酸盐岩岩溶含水层作为研究区。数据包括该区域内2009—2012年布设的16口观测井及其长期地下水位监测序列、30 m分辨率数字高程模型(digital elevation model,DEM)数据。将地下水位、地下水位时间序列的过去步长、降雨量、降雨量序列的过去步长和同类别井(相互间具有强连通性)的地下水位序列作为输入变量。在输入数据集中,将2009年1月—2011年12月阶段划分为训练集,2012年1—12月为预测集。并且在每批次训练中,将训练集的后20%划分为验证集用于数据验证和调整参数,数据集划分如表4所示。
为了验证考虑基于混合聚类结果的连通性特征的ConvLSTM神经网络模型M-MV-ConvLSTM在预测地下水位时的有效性,还将与单变量SV-LSTM模型、多变量MV-LSTM模型、仅考虑空间距离的多变量D-MV-ConvLSTM模型进行对比分析。
模型参数通过大量案例调整情况下给出。隐藏节点的数量、卷积层的核大小和学习率共包含45种组合,因此在验证阶段通过试错法确定一个最优组合。每个模型的最佳参数组合如表5所示。
对于SV-LSTM、MV-LSTM、D-MV-ConvLSTM和M-MV-ConvLSTM模型,平均均方根误差值(root mean square error,RMSE)分别为1.38、0.75、0.56和0.46。实验结果表明,考虑降雨因素MV-LSTM模型在每口井的表现均优于SV-LSTM模型。考虑了GWLd的D-MV-ConvLSTM模型比SV-LSTM和MV-LSTM模型表现更好。此外,M-MV-ConvLSTM模型考虑了观测井之间的连通性,其精度得到进一步提高。表6列出了4个地下水位预测结果的RMSE和纳什效率系数(Nash-Sutcliffe efficiency,NSE)。图12为预测结果的RMSE直方图。
表6中NSE可以看出,D-MV-ConvLSTM和M-MV-ConvLSTM模型的NSE与SV-LSTM模型和MV-LSTM相比都有一定程度的改进。与D-MV-ConvLSTM相比,M-MV-ConvLSTM模型的NSE值进一步提高。使用该模型,在所有井中,50%的井的NSE大于0.9,80%井的NSE大于0.85,说明同时考虑了气象因素和混合聚类结果连通性强弱的M-MV-ConvLSTM模型预测效果最好,可信度高。
图13为选定的部分井使用4种模型得到的预测结果。预测数据为2012年1—12月的地下水位观测数据,每月采样6 次,采样间隔为5 d。可以看出,4个模型的预测值和实际观测值的趋势是一致的。由于M-MV-ConvLSTM模型不仅考虑了目标观测井本身的地下水位数据和气象数据,还考虑了相关观测井的地下水位数据。因此M-MV-ConvLSTM模型的预测结果比其他3个模型的预测结果更符合实际观察结果。
与单一结构的LSTM模型相比,ConvLSTM模型综合分析了数据的时空特征,对预测模型的时滞问题有一定的改善。从图13所示的各井预测结果可以看出,M-MV-ConvLSTM模型大大改善了预测滞后问题。考虑到预测精度和滞后问题的改善,所提出的考虑观测井连通性的M-MV-ConvLSTM预测模型对地下水位的预测具有较好的适用性。
针对地下水位预测考虑因素不全面的问题,提出一种混合聚类方法,其考虑了观测井间连通性因素。并构建ConvLSTM地下水预测模型,与传统的LSTM预测模型对比,得到以下结论。
(1)根据观测井间的距离和含水层水文地质特征,提出了基于距离-属性的混合聚类方法,综合分析了岩溶含水层的连通性,并在岩溶含水层地下水位预测中有效证明观测井间连通性的强弱会对预测结果产生明显差异,体现了在预测过程中考虑连通性因素的重要性。
(2)把LSTM模型与CNN模型相结合,提出了ConvLSTM模型,使其不仅具有LSTM的时间建模能力,而且还可以描绘局部特征,相比传统的LSTM预测模型而言其精确度与可靠性得到了进一步提高。
(3)验证连通性因素在地下水预测中的有效性,考虑基于混合聚类结果的连通性特征的M-MV-ConvLSTM模型与单变量SV-LSTM模型、多变量MV-LSTM模型和仅考虑空间距离模型D-MV-ConvLSTM对比分析。分析得出平均RMSE为0.457,NSE为0.216,结果表明,考虑观测井间连通性特征的M-MV-ConvLSTM模型具有更高的预测精度,体现了连通性因素和M-MV-ConvLSTM模型的有效性、创新性。
  • 国家外国专家项目(G2022023020L)
  • 山东省重大科技创新工程(2019JZZY020105)
  • 甘肃省重点研发计划(22YF7FH224)
参考文献 引证文献
排序方式:
[1]
张召悦, 张红波. 基于ARMA-AE-LSTM模型的进场交通流预测方法[J]. 科学技术与工程, 2024, 24(27): 11919-11927.
Zhang Zhaoyue, Zhang Hongbo. Approach traffic flow prediction method based on ARMA-AE-LSTM Model[J], Science Technology and Engineering, 2024, 24(27): 11919-11927.
[2]
孙虹洁, 赵振华, 黄林显, . 多变量LSTM神经网络模型在地下水位预测中的应用[J]. 人民黄河, 2022, 44(8): 69-75.
Sun Hongjie, Zhao Zhenhua, Hang Linxian, et al. Application of multivariate LSTM neural network model in groundwater level prediction[J]. Yellow River, 2022, 44(8): 69-75.
[3]
张朝逢, 陈皓锐, 岳中奇. 基于长短时记忆网络(LSTM)的地下水埋深模拟预测——以关中平原为例的实例分析[J]. 中国农村水利水电, 2020(9): 127-131, 137.
Zhang Chaofeng, Chen Haorui, Yue Zhongqi. Simulation and prediction of groundwater depth based on long short-term memory network (LSTM): a case study of Guanzhong Plain[J]. China Rural Water and Hydropower, 2020(9): 127-131, 137.
[4]
陈守开, 蒋海峰, 李海瑞, . 基于RST-LSTM模型的堤坝渗压动态预测分析[J]. 应用基础与工程科学学报, 2021, 29(1): 112-122.
Chen Shoukai, Jiang Haifeng, Li Hairui, et al. Dynamic prediction analysis of dam seepage pressure based on RST-LSTM model[J]. Journal of Basic Science and Engineering, 2021, 29(1): 112-122.
[5]
牛欣怡, 鲁程鹏, 卢佳赟, . 机器学习模型在地下水埋深模拟中的适应性分析[J]. 河海大学学报(自然科学版), 2022, 50(4): 74-82.
Niu Xinyi, Lu Chengpeng, Lu Jiayun, et al. Adaptability analysis of machine learning model in groundwater depth simulation[J]. Journal of Hohai University(Natural Sciences), 2022, 50(4): 74-82.
[6]
陈聪, 候磊, 李乐乐, . 基于GRU改进RNN神经网络的飞机燃油流量预测[J]. 科学技术与工程, 2021, 21(27): 11663-11673.
Chen Cong, Hou Lei, Li Lele, et al. Prediction of aircraft fuel flow based on recurrent neural network[J]. Science Technology and Engineering, 2021, 21(27): 11663-11673.
[7]
闫佰忠, 孙剑, 王昕洲, . 基于多变量LSTM神经网络的地下水水位预测[J]. 吉林大学学报(地球科学版), 2020, 50(1): 208-216.
Yan Baizhong, Sun Jian, Wang Xinzhou, et al. Groundwater level prediction based on multivariate LSTM neural network[J]. Journal of Jilin University(Earth Science Edition), 2020, 50(1): 208-216.
[8]
汪云, 杨海博, 徐建, . 基于长短期记忆神经网络模型的地下水水位预测研究[J]. 节水灌溉, 2019(10): 73-77.
Wang Yun, Yang Haibo, Xun Jian, et al. Research on groundwater level prediction based on long short-term memory neural network model[J]. Water Saving Irrigation, 2019(10): 73-77.
[9]
冯希尧, 苟俊程, 刘瑞, . 基于遗传算法优化机器学习模型的地下水潜在性预测[J]. 科学技术与工程, 2024, 24(19): 7988-7998.
Feng Xiyao, Gou Juncheng, Liu Rui, et al. Prediction of groundwater potential based on genetic algorithm optimized machine learning model[J]. Science Technology and Engineering, 2024, 24(19): 7988-7998.
[10]
胡飞跃, 王忠忠. 基于降雨量的SWA-LSTM深度学习模型在地下水位预测中的应用研究[J]. 地下水, 2022, 44(6): 70-72, 113.
Hu Feiyue, Wang Zhongzhong. The application of SWA-LSTM deep learning model based on rainfall in groundwater level prediction[J]. Ground Water, 2022, 44(6): 70-72, 113.
[11]
侯金霄, 黄林显, 胡晓农, . 基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用[J]. 水资源与水工程学报, 2023, 34(4): 92-98.
Hou Jinxiao, Hang Linxian, Hu Xiaonong, et al. Application of karst groundwater level prediction in Baotu Spring based on EMD-LSTM coupling model[J]. Journal of Water Resources and Water Engineering, 2023, 34(4): 92-98.
[12]
郭艺, 秦大军, 王枫, . 基于时间序列分析法的岩溶泉水位预测[J]. 中国岩溶, 2021, 40(4): 689-697.
Guo Yi, Qin Dajun, Wang Feng, et al. Prediction of karst spring water level based on time series analysis method[J]. Carsologica Sinica, 2021, 40(4): 689-697.
[13]
冯鹏宇, 金韬, 沈一选, . 基于CNN-Transformer的城区地下水位预测[J]. 计算机仿真, 2023, 40(4): 492-498.
Feng Pengyu, Jin Tao, Shen Yixuan, et al. Prediction of urban groundwater level based on CNN-Transformer[J]. Computer Simulation, 2023, 40(4): 492-498.
[14]
张研, 郭道静, 张树光, . 岩溶区灰岩溶蚀程度卷积神经网络识别及敏感性分析[J]. 应用基础与工程科学学报, 2023, 31(4): 961-976.
Zhang Yan, Guo Daojing, Zhang Shuguang, et al. Convolutional neural network identification and sensitivity analysis of limestone dissolution degree in karst area[J]. Journal of Basic Science and Engineering, 2023, 31(4): 961-976.
[15]
任青阳, 王彦丁, 施俭. 卷积神经网络目标检测算法研究进展[J]. 科学技术与程, 2024, 24(32): 13665-13677.
Ren Qingyang, Wang Yanding, Shi Jian. Advances in target detection algorithms for convolutional neural networks[J]. Science Technology and Engineering, 2024, 24(32): 13665-13677.
[16]
郭靖. 对K-means聚类算法欧氏距离加权系数的研究[J]. 网络安全技术与应用, 2016(10): 74-75.
Guo Jing. Research on the Euclidean distance weighted coefficient of K-means clustering algorithm[J]. Network Security Technology & Application, 2016(10): 74-75.
[17]
金福喜, 袁权威, 秦帅帅. 基于GIS和K-means聚类方法的滑坡气象预警模型[J]. 金属矿山, 2018(6): 162-166.
Jin Fuxi, Yuan Quanwei, Qin Shuaishuai. Landslide meteorological early warning model based on GIS and K-means clustering method[J]. Metal Mine, 2018(6): 162-166.
[18]
Yuan C H, Yang H T. Research on K-value selection method of K-means clustering algorithm[J]. Multidisciplinary Scientific Journal, 2019, 2(2): 226-235.
[19]
程亚南, 王晓峰, 刘凇佐, . 求解多起点多旅行商问题的K-means聚类信息传播算法[J]. 科学技术与工程, 2022, 22(23): 10146-10154.
Cheng Yanan, Wang Xiaofeng, Liu Songzuo, et al. K-means clustering information propagation algorithm for multiple depots multiple traveling salesman problem[J]. Science Technology and Engineering, 2022, 22(23): 10146-10154.
[20]
蒋溢, 伍书平, 胡昆, . 基于Lasso和构造性覆盖算法的不均衡数据分类方法[J]. 计算机应用, 2023, 43(4): 1086-1093.
Jiang Yi, Wu Shuping, Hu Kun, et al. Imbalanced data classification method based on Lasso and constructive covering algorithm[J]. Journal of Computer Applications, 2023, 43(4): 1086-1093.
2025年第25卷第20期
PDF下载
71
33
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405660
  • 接收时间:2024-07-28
  • 首发时间:2026-05-13
  • 出版时间:2025-07-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-28
  • 修回日期:2025-04-15
基金
国家外国专家项目(G2022023020L)
山东省重大科技创新工程(2019JZZY020105)
甘肃省重点研发计划(22YF7FH224)
作者信息
    1 山东建筑大学土木工程学院, 济南 250101
    2 济南轨道交通集团有限公司, 济南 250014

通讯作者:

* 李虎(1983—),男,汉族,山东济南人,博士,高级工程师。研究方向:轨道交通工程建设。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405660
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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