Article(id=1224795176200192232, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1224795175415857383, articleNumber=null, orderNo=null, doi=10.12284/hyxb2022015, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1612713600000, receivedDateStr=2021-02-08, revisedDate=1633449600000, revisedDateStr=2021-10-06, acceptedDate=null, acceptedDateStr=null, onlineDate=1769943525600, onlineDateStr=2026-02-01, pubDate=1646064000000, pubDateStr=2022-03-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1769943525600, onlineIssueDateStr=2026-02-01, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1769943525600, creator=13701087609, updateTime=1769943525600, updator=13701087609, issue=Issue{id=1224795175415857383, tenantId=1146029695717560320, journalId=1149651085930835976, year='2022', volume='44', issue='3', pageStart='1', pageEnd='146', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1769943525413, creator=13701087609, updateTime=1769995902698, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1225014861743145000, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1224795175415857383, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1225014861747339305, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1224795175415857383, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=81, endPage=97, ext={EN=ArticleExt(id=1224795176527347946, articleId=1224795176200192232, tenantId=1146029695717560320, journalId=1149651085930835976, language=EN, title=Seawater intrusion characterization and dynamics prediction based on WA-NARX hybrid model in the south of Laizhou Bay, columnId=1194652705852465724, journalTitle=Haiyang Xuebao, columnName=Article, runingTitle=null, highlight=null, articleAbstract=

With the rapid economic development and increasing anthropogenic activities, the groundwater in the coastal area has been excessively exploited. The resulting seawater intrusion has become a widely distributed environmental geological problem. Taken the coastal area of Laizhou Bay as a research area, the dynamics of groundwater level (GWL) and electrical conductivity (EC) were analyzed with the continuous monitoring data. Based on the rainfall, evaporation, tide and agricultural irrigation and drainage electricity consumption that affect the groundwater variation, the hybrid model of wavelet analysis (WA) and NARX neural network was introduced to predict the dynamics of GWL and EC. The root mean square error (RMSE) and goodness of fit (R2) were used to measure the prediction accuracy. The results showed that the annual variation of GWL was characterized by a type of rainfall infiltration-exploitation. A significant correlation at the frequency of 0.5 d was observed between groundwater level and tide, and the influence of tide on EC was weaker than that on GWL. For the dynamics prediction with WA-NARX method, the RMSE was less than 0.03 and R2 was greater than 0.98 in both the training and testing stages. The results indicated the hybrid model had a good performance and could effectively predict the dynamics of GWL and EC. The effects of different influencing factors as model input parameters on the prediction results were further compared. The results showed that rainfall and tide parameters were the main variables affecting the GWL and EC variations in the coastal zone. The pumping information reflected by the evaporation and agricultural drainage and irrigation power consumption also affected the groundwater dynamics. The degree of influence was related to the observation frequency. The research results can provide theoretical and technical support for real-time monitoring, prediction and early warning of seawater intrusion in coastal zone.

, correspAuthors=Xiaoying Zhang, Guangquan Chen, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2022 Pratacultural Science. 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, authorCompany=null, fund=null, authors=null, authorsList=Fan Dong, Xiaoying Zhang, Guangquan Chen, Zhenxue Dai, Yancheng Wang), CN=ArticleExt(id=1224795180658737484, articleId=1224795176200192232, tenantId=1146029695717560320, journalId=1149651085930835976, language=CN, title=莱州湾南岸海水入侵特征及基于WA-NARX混合模型的动态预测, columnId=1149698756456657529, journalTitle=海洋学报, columnName=论文, runingTitle=null, highlight=null, articleAbstract=

随着我国海岸带经济的快速发展与人类活动的加剧,地下水超采现象十分严峻,由此引发的海水入侵已成为滨海地区普遍存在的地质问题。本研究以莱州湾南岸海水入侵区为研究对象,根据地下水连续监测数据分析了地下水位和电导率的动态变化特征。在此基础上,基于降雨、蒸发、潮汐及农业排灌用电量等影响地下水动态变化的因素,建立了小波分析(WA)与具有外部输入的非线性自回归神经网络(NARX)的混合模型,对地下水水位和电导率进行动态预测,并采用均方根误差和拟合度对预测结果进行评价。研究结果表明,莱州湾南岸地下水年内动态变化特征为降雨入渗–开采型,地下水位和潮汐之间在0.5 d频率上呈现较高相关性,潮汐对地下水电导率的影响要弱于对地下水位的影响;WA-NARX混合模型在训练和测试阶段的均方根误差均小于0.03且拟合度大于0.98,可有效预测研究区海水入侵的变化程度。同时,为验证模型适用性,对比了不同影响因素作为模型输入参数对预测结果的影响。结果表明,降雨和潮汐参数是影响海岸带地下水位和电导率的主要变量,蒸发以及农业排灌用电量反映的部分抽水信息对地下水位和电导率也有影响,其影响程度与观测频率相关。本文研究结果可为海岸带海水入侵的实时监测、预测、预警提供理论与技术支撑。

, correspAuthors=张晓影, 陈广泉, authorNote=null, correspAuthorsNote=
张晓影,女,副教授,博士生导师,主要从事非均质介质中溶质反应迁移模拟及尺度效应研究。E-mail:
陈广泉,男,高级工程师,主要从事海洋地质与海水入侵研究。E-mail:
, copyrightStatement=版权所有©《海洋学报》编辑部 2022, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=85DoDPk77jkZBwh2EQm9pw==, magXml=0AVbsMS/s1LfHII+sCN8ow==, pdfUrl=null, pdf=Zim6ku4kELD5INasqJd4WQ==, pdfFileSize=3557050, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=uvSspntN1EcEJ0KiU4YHVg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=St9JtPNHaNeWFn2aPsWoFA==, mapNumber=null, authorCompany=null, fund=null, authors=

董凡(1997—),男,陕西省商洛市人,主要从事基于深度学习的地下水位预测研究。E-mail:

, authorsList=董凡, 张晓影, 陈广泉, 戴振学, 王延诚)}, authors=[Author(id=1225366058937271221, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dongfan19@mails.jlu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225366059226678221, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366058937271221, language=EN, stringName=Fan Dong, firstName=Fan, middleName=null, lastName=Dong, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. College of Construction Engineering, Jilin University, Changchun 130026, China
2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225366059335730131, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366058937271221, language=CN, stringName=董凡, firstName=凡, middleName=null, lastName=董, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.吉林大学 建设工程学院,吉林 长春 130026
2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061, bio={"content":"

董凡(1997—),男,陕西省商洛市人,主要从事基于深度学习的地下水位预测研究。E-mail:

"}, bioImg=null, bioContent=

董凡(1997—),男,陕西省商洛市人,主要从事基于深度学习的地下水位预测研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225366058597532571, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058605921180, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. College of Construction Engineering, Jilin University, Changchun 130026, China), AuthorCompanyExt(id=1225366058618504094, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.吉林大学 建设工程学院,吉林 长春 130026)]), AuthorCompany(id=1225366058698195874, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058710778787, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China), AuthorCompanyExt(id=1225366058727556004, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061)])]), Author(id=1225366059411227612, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xiaoyingzh@jlu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1225366059549639659, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366059411227612, language=EN, stringName=Xiaoying Zhang, firstName=Xiaoying, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1. College of Construction Engineering, Jilin University, Changchun 130026, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225366059679663091, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366059411227612, language=CN, stringName=张晓影, firstName=晓影, middleName=null, lastName=张, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1.吉林大学 建设工程学院,吉林 长春 130026, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225366058597532571, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058605921180, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. College of Construction Engineering, Jilin University, Changchun 130026, China), AuthorCompanyExt(id=1225366058618504094, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.吉林大学 建设工程学院,吉林 长春 130026)])]), Author(id=1225366059780326393, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenguangquan@fio.org.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1225366059889378302, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366059780326393, language=EN, stringName=Guangquan Chen, firstName=Guangquan, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, *, address=2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China
3. Laboratory for Marine Geology, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266237, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225366060073926661, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366059780326393, language=CN, stringName=陈广泉, firstName=广泉, middleName=null, lastName=陈, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, *, address=2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061
3.青岛海洋科学与技术试点国家实验室 海洋地质过程与环境功能实验室,山东 青岛 266237, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225366058698195874, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058710778787, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China), AuthorCompanyExt(id=1225366058727556004, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061)]), AuthorCompany(id=1225366058836607915, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058844996525, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058836607915, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3. Laboratory for Marine Geology, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266237, China), AuthorCompanyExt(id=1225366058853385134, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058836607915, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.青岛海洋科学与技术试点国家实验室 海洋地质过程与环境功能实验室,山东 青岛 266237)])]), Author(id=1225366060162007051, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, 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=1225366060266864658, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366060162007051, language=EN, stringName=Zhenxue Dai, firstName=Zhenxue, middleName=null, lastName=Dai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. College of Construction Engineering, Jilin University, Changchun 130026, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225366060380110870, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366060162007051, language=CN, stringName=戴振学, firstName=振学, middleName=null, lastName=戴, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.吉林大学 建设工程学院,吉林 长春 130026, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225366058597532571, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058605921180, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. College of Construction Engineering, Jilin University, Changchun 130026, China), AuthorCompanyExt(id=1225366058618504094, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.吉林大学 建设工程学院,吉林 长春 130026)])]), Author(id=1225366060447219742, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, 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=1225366060560465961, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366060447219742, language=EN, stringName=Yancheng Wang, firstName=Yancheng, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China
3. Laboratory for Marine Geology, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266237, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225366060635963440, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, authorId=1225366060447219742, language=CN, stringName=王延诚, firstName=延诚, middleName=null, lastName=王, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061
3.青岛海洋科学与技术试点国家实验室 海洋地质过程与环境功能实验室,山东 青岛 266237, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225366058698195874, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058710778787, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China), AuthorCompanyExt(id=1225366058727556004, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061)]), AuthorCompany(id=1225366058836607915, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058844996525, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058836607915, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3. Laboratory for Marine Geology, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266237, China), AuthorCompanyExt(id=1225366058853385134, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058836607915, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.青岛海洋科学与技术试点国家实验室 海洋地质过程与环境功能实验室,山东 青岛 266237)])])], keywords=[Keyword(id=1225366060828901436, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, orderNo=1, keyword=seawater intrusion), Keyword(id=1225366060925370432, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, orderNo=2, keyword=groundwater level), Keyword(id=1225366061013450825, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, orderNo=3, keyword=electrical conductivity), Keyword(id=1225366061097336913, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, orderNo=4, keyword=wavelet analysis), Keyword(id=1225366061172834389, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, orderNo=5, keyword=NARX neural network), Keyword(id=1225366061290274909, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, orderNo=6, keyword=prediction), Keyword(id=1225366061374160997, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, orderNo=1, keyword=海水入侵), Keyword(id=1225366061483212906, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, orderNo=2, keyword=地下水水位), Keyword(id=1225366061579681903, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, orderNo=3, keyword=电导率), Keyword(id=1225366061655179379, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, orderNo=4, keyword=小波分析), Keyword(id=1225366061739065464, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, orderNo=5, keyword=NARX神经网络), Keyword(id=1225366061856505981, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, orderNo=6, keyword=预测)], refs=[Reference(id=1225366066923225437, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, 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=吴吉春, 吴永祥, 林锦, 等. 黄渤海沿海地区地下水管理与海水入侵防治研究[J]. 中国环境管理, 2018, 10(2): 91−92., articleTitle=null, refAbstract=null), Reference(id=1225366066981945696, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Jichun, Wu Yongxiang, Lin Jin, et al. Study on the groundwater management and seawater intrusion prevention in the coastal areas of the Bohai Sea and the Yellow Sea[J]. Chinese Journal of Environmental Management, 2018, 10(2): 91−92., articleTitle=null, refAbstract=null), Reference(id=1225366067057443171, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=高茂生, 骆永明. 我国重点海岸带地下水资源问题与海水入侵防控[J]. 中国科学院院刊, 2016, 31(10): 1197−1203., articleTitle=null, refAbstract=null), Reference(id=1225366067158106470, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Maosheng, Luo Yongming. Change of groundwater resource and prevention and control of seawater intrusion in coastal zone[J]. Bulletin of Chinese Academy of Sciences, 2016, 31(10): 1197−1203., articleTitle=null, refAbstract=null), Reference(id=1225366067250381161, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiaoying, Qi Linlin, Li Wenming, et al. Bacterial community variations with salinity in the saltwater-intruded estuarine aquifer[J]. Science of the Total Environment, 2021, 755: 142423., articleTitle=null, refAbstract=null), Reference(id=1225366067363627372, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiaoying, Hu B X, Wang Peng, et al. Hydrogeochemical evolution and heavy metal contamination in groundwater of a reclaimed land on Zhoushan Island[J]. Water, 2018, 10(3): 316: 1−22., articleTitle=null, refAbstract=null), Reference(id=1225366067476873585, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=孙娜, 周建中, 朱双, 等. 基于小波分析的两种神经网络耦合模型在月径流预测中的应用[J]. 水电能源科学, 2018, 36(4): 14−17, 32., articleTitle=null, refAbstract=null), Reference(id=1225366067556565362, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Na, Zhou Jianzhong, Zhu Shuang, et al. Application of hybrid models based on wavelet analysis and two different neural networks in prediction of monthly runoff[J]. Water Resources and Power, 2018, 36(4): 14−17, 32., articleTitle=null, refAbstract=null), Reference(id=1225366067632062837, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Shoaib M, Shamseldin A Y, Melville B W, et al. A comparison between wavelet based static and dynamic neural network approaches for runoff prediction[J]. Journal of Hydrology, 2016, 535: 211−225., articleTitle=null, refAbstract=null), Reference(id=1225366067728531833, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Guzman S M, Paz J O, Tagert M L M. The use of NARX neural networks to forecast daily groundwater levels[J]. Water Resources Management, 2017, 31(5): 1591−1603., articleTitle=null, refAbstract=null), Reference(id=1225366067913081210, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Wunsch A, Liesch T, Broda S. Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX)[J]. Journal of Hydrology, 2018, 567: 743−758., articleTitle=null, refAbstract=null), Reference(id=1225366067992772989, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Di Nunno F, Granata F. Groundwater level prediction in Apulia region (Southern Italy) using NARX neural network[J]. Environmental Research, 2020, 190: 110062., articleTitle=null, refAbstract=null), Reference(id=1225366068110213505, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Cannas B, Fanni A, See L, et al. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning[J]. Physics and Chemistry of the Earth, Parts A/B/C, 2006, 31(18): 1164−1171., articleTitle=null, refAbstract=null), Reference(id=1225366068210876804, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Juan, Qiu Han, Li Xiaoyu, et al. Real-time nowcasting of microbiological water quality at recreational beaches: a wavelet and artificial neural network-based hybrid modeling approach[J]. Environmental Science & Technology, 2018, 52(15): 8446−8455., articleTitle=null, refAbstract=null), Reference(id=1225366068282179974, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Nason G P, Von Sachs R. Wavelets in time-series analysis[J]. Philosophical Transactions of the Royal Society A: Mathematical, Physical, and Engineering Sciences, 1999, 357(1760): 2511−2526., articleTitle=null, refAbstract=null), Reference(id=1225366068382843272, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Moosavi V, Vafakhah M, Shirmohammadi B, et al. A Wavelet-ANFIS hybrid model for groundwater level forecasting for different prediction periods[J]. Water Resources Management, 2013, 27(5): 1301−1321., articleTitle=null, refAbstract=null), Reference(id=1225366068466729354, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiaoying, Dong Fan, Dai Heng, et al. Influence of lunar semidiurnal tides on groundwater dynamics in estuarine aquifers[J]. Hydrogeology Journal, 2020, 28(4): 1419−1429., articleTitle=null, refAbstract=null), Reference(id=1225366068575781263, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Kisi O, Shiri J. Precipitation forecasting using wavelet-genetic programming and wavelet-neuro-fuzzy conjunction models[J]. Water Resources Management, 2011, 25(13): 3135−3152., articleTitle=null, refAbstract=null), Reference(id=1225366068689027474, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Mohanty S, Jha M K, Raul S K, et al. Using artificial neural network approach for simultaneous forecasting of weekly groundwater levels at multiple sites[J]. Water Resources Management, 2015, 29(15): 5521−5532., articleTitle=null, refAbstract=null), Reference(id=1225366068781302165, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Nourani V, Alami M T, Vousoughi F D, et al. Wavelet-entropy data pre-processing approach for ANN-based groundwater level modeling[J]. Journal of Hydrology, 2015, 524: 255−269., articleTitle=null, refAbstract=null), Reference(id=1225366068873576856, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Adamowski J, Chan H F. A wavelet neural network conjunction model for groundwater level forecasting[J]. Journal of Hydrology, 2011, 407(1/4): 28−40., articleTitle=null, refAbstract=null), Reference(id=1225366068961657244, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Gorgij A D, Kisi O, Moghaddam A A. Groundwater budget forecasting, using hybrid wavelet-ANN-GP modelling: a case study of Azarshahr Plain, East Azerbaijan, Iran[J]. Hydrology Research, 2017, 48(2): 455−467., articleTitle=null, refAbstract=null), Reference(id=1225366069045543325, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=张建锋, 刘见宝, 崔树军, 等. 小波–神经网络混合模型预测地下水水位[J]. 长江科学院院报, 2016, 33(8): 18−21., articleTitle=null, refAbstract=null), Reference(id=1225366069150400930, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jianfeng, Liu Jianbao, Cui Shujun, et al. A wavelet-ANN hybrid model for groundwater level forecasting[J]. Journal of Yangtze River Scientific Research Institute, 2016, 33(8): 18−21., articleTitle=null, refAbstract=null), Reference(id=1225366069246869923, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Seo Y, Kim S, Kisi O, et al. Daily water level forecasting using wavelet decomposition and artificial intelligence techniques[J]. Journal of Hydrology, 2015, 520: 224−243., articleTitle=null, refAbstract=null), Reference(id=1225366069343338919, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Juan, Zhang Xiaoying, Niu Jie, et al. Prediction of groundwater level in seashore reclaimed land using wavelet and artificial neural network-based hybrid model[J]. Journal of Hydrology, 2019, 577: 123948., articleTitle=null, refAbstract=null), Reference(id=1225366069427225001, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=陈广泉. 莱州湾地区海水入侵的影响机制及预警评价研究[D]. 上海: 华东师范大学, 2013., articleTitle=null, refAbstract=null), Reference(id=1225366069502722474, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Guangquan. Mechanisms underlying of seawater intrusion and evaluation of early warning systems in the Laizhou Bay area[D]. Shanghai: East China Normal University, 2013., articleTitle=null, refAbstract=null), Reference(id=1225366069607580079, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Guangquan, Xiong Guiyao, Lin Jin, et al. Elucidating the pollution sources and groundwater evolution in typical seawater intrusion areas using hydrochemical and environmental stable isotope technique: a case study for Shandong Province, China[J]. Lithosphere, 2021, 2021(S3): 4227303., articleTitle=null, refAbstract=null), Reference(id=1225366069716631987, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=苗晋杰. 莱州湾南岸海(咸)水入侵动态监测及演化研究[D]. 北京: 中国地质大学(北京), 2014., articleTitle=null, refAbstract=null), Reference(id=1225366069796323763, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Miao Jinjie. Dynamic monitoring and evolution study of saline intrusion at south coast of LaiZhou Bay[D]. Beijing: China University of Geosciences (Beijing), 2014., articleTitle=null, refAbstract=null), Reference(id=1225366069855044023, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiaoying, Miao Jinjie, Hu B X, et al. Hydrogeochemical characterization and groundwater quality assessment in intruded coastal brine aquifers (Laizhou Bay, China)[J]. Environmental Science and Pollution Research, 2017, 24(26): 21073−21090., articleTitle=null, refAbstract=null), Reference(id=1225366069926347194, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Gedalof Z, Smith D J. Interdecadal climate variability and regime-scale shifts in Pacific North America[J]. Geophysical Research Letters, 2001, 28(8): 1515−1518., articleTitle=null, refAbstract=null), Reference(id=1225366070018621885, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Grinsted A, Moore J C, Jevrejeva S. Application of the cross wavelet transform and wavelet coherence to geophysical time series[J]. Nonlinear Processes in Geophysics, 2004, 11(5/6): 561−566., articleTitle=null, refAbstract=null), Reference(id=1225366070098313665, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Mallat S G. A theory for multiresolution signal decomposition: the wavelet representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674−693., articleTitle=null, refAbstract=null), Reference(id=1225366070178005445, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Shensa M J. The discrete wavelet transform: wedding the a trous and Mallat algorithms[J]. IEEE Transactions on Signal Processing, 1992, 40(10): 2464−2482., articleTitle=null, refAbstract=null), Reference(id=1225366070245114311, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Elman J L. Finding structure in time[J]. Cognitive Science, 1990, 14(2): 179−211., articleTitle=null, refAbstract=null), Reference(id=1225366070333194698, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin T, Horne B G, Tino P, et al. Learning long-term dependencies in NARX recurrent neural networks[J]. IEEE Transactions on Neural Networks, 1996, 7(6): 1329−1338., articleTitle=null, refAbstract=null), Reference(id=1225366070421275085, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Chatterjee S, Nigam S, Singh J B, et al. Software fault prediction using Nonlinear Autoregressive with eXogenous Inputs (NARX) network[J]. Applied Intelligence, 2012, 37(1): 121−129., articleTitle=null, refAbstract=null), Reference(id=1225366070488383952, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=柴琳娜, 屈永华, 张立新, 等. 基于自回归神经网络的时间序列叶面积指数估算[J]. 地球科学进展, 2009, 24(7): 756−768., articleTitle=null, refAbstract=null), Reference(id=1225366070572270036, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Chai Linna, Qu Yonghua, Zhang Lixin, et al. Estimating time series leaf area index based on recurrent neural networks[J]. Advances in Earth Science, 2009, 24(7): 756−768., articleTitle=null, refAbstract=null), Reference(id=1225366070651961815, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Adamowski J, Sun K R. Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds[J]. Journal of Hydrology, 2010, 390(1/2): 85−91., articleTitle=null, refAbstract=null), Reference(id=1225366070735847898, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Tiwari M K, Chatterjee C. Development of an accurate and reliable hourly flood forecasting model using wavelet-bootstrap-ANN (WBANN) hybrid approach[J]. Journal of Hydrology, 2010, 394(3/4): 458−470., articleTitle=null, refAbstract=null), Reference(id=1225366070819733982, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=苗青. 降雨与潮汐作用对莱州湾地区海水入侵的影响机制研究[D]. 青岛: 国家海洋局第一海洋研究所, 2013., articleTitle=null, refAbstract=null), Reference(id=1225366070924591581, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Miao Qing. Effects of precipitation and tide on seawater intrusion in the Laizhou Bay[D]. Qingdao: The First Institute of Oceanography, State Oceanic Administration, 2013., articleTitle=null, refAbstract=null), Reference(id=1225366071033643487, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=李志威, 张晓影, 张明珠, 等. 海水入侵指标对比分析与评价——以珠江口地下水含水层为例[J]. 海洋环境科学, 2020, 39(1): 16−24., articleTitle=null, refAbstract=null), Reference(id=1225366071117529568, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zhiwei, Zhang Xiaoying, Zhang Mingzhu, et al. Comparison of indicators for the assessment of saltwater intrusion in coastal aquifers—taking aquifers in Pearl River Estuary as an example[J]. Marine Environmental Science, 2020, 39(1): 16−24., articleTitle=null, refAbstract=null), Reference(id=1225366071209804259, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=王玉广, 王传珺, 刘志华, 等. 地下水位和海平面变化对绥中砂质海岸海水入侵影响[J]. 海洋环境科学, 2019, 38(3): 347−352., articleTitle=null, refAbstract=null), Reference(id=1225366071297884645, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yuguang, Wang Chuanjun, Liu Zhihua, et al. Impact to the the seawater intrusion around sand coast in Suizhong with the variations of groundwater level and sea level[J]. Marine Environmental Science, 2019, 38(3): 347−352., articleTitle=null, refAbstract=null), Reference(id=1225366071394353639, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=覃光雄, 胡晓农, 张晓影, 等. 珠江河口区地下水盐分空间变异特征分析[J]. 海洋环境科学, 2018, 37(6): 835−842., articleTitle=null, refAbstract=null), Reference(id=1225366071478239722, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Qin Guangxiong, Hu Xiaonong, Zhang Xiaoying, et al. Characterization of groundwater salinity spatial variation in the Pearl River estuary[J]. Marine Environmental Science, 2018, 37(6): 835−842., articleTitle=null, refAbstract=null), Reference(id=1225366071566320109, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=刘启和. 辽阳市地下水电导率特性研究[J]. 水利技术监督, 2017, 25(3): 60−62, 91., articleTitle=null, refAbstract=null), Reference(id=1225366071675372017, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Qihe. Study on conductivity characteristics of groundwater in Liaoyang City[J]. Technical Supervision in Water Resources, 2017, 25(3): 60−62, 91., articleTitle=null, refAbstract=null), Reference(id=1225366071759258099, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=章斌, 宋献方, 韩冬梅, 等. 运用数理统计和模糊数学评价秦皇岛洋戴河平原的海水入侵程度[J]. 地理科学, 2013, 33(3): 342−348., articleTitle=null, refAbstract=null), Reference(id=1225366071864115702, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Bin, Song Xianfang, Han Dongmei, et al. Seawater intrusion degree evaluation based on mathematical statistics and fuzzy mathematics in Qinhuangdao Yangdai River plain[J]. Scientia Geographica Sinica, 2013, 33(3): 342−348., articleTitle=null, refAbstract=null), Reference(id=1225366071939613176, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=赵世彬, 陈广泉, 张晓影, 等. 潮汐影响下的海岸带地下河口水交换及其生物地球化学效应[J]. 海洋地质前沿, 2018, 34(9): 73−78., articleTitle=null, refAbstract=null), Reference(id=1225366071998333433, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Shibin, Chen Guangquan, Zhang Xiaoying, et al. Water exchange and biogeochemical effects of subterranean estuary with tide[J]. Marine Geology Frontiers, 2018, 34(9): 73−78., articleTitle=null, refAbstract=null)], funds=[Fund(id=1225366066549932365, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, awardId=2018SDKJ0503-2, language=CN, fundingSource=山东省重大科技创新工程专项(2018SDKJ0503-2), fundOrder=null, country=null), Fund(id=1225366066621235536, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, awardId=41702244, language=CN, fundingSource=国家自然科学基金面上项目(41702244), fundOrder=null, country=null), Fund(id=1225366066700927316, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, awardId=41972249,41706067, language=CN, fundingSource=国家自然科学基金青年项目(41972249,41706067), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1225366058597532571, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058605921180, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. College of Construction Engineering, Jilin University, Changchun 130026, China), AuthorCompanyExt(id=1225366058618504094, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058597532571, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.吉林大学 建设工程学院,吉林 长春 130026)]), AuthorCompany(id=1225366058698195874, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058710778787, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China), AuthorCompanyExt(id=1225366058727556004, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058698195874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061)]), AuthorCompany(id=1225366058836607915, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, xref=null, ext=[AuthorCompanyExt(id=1225366058844996525, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058836607915, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3. Laboratory for Marine Geology, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266237, China), AuthorCompanyExt(id=1225366058853385134, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, companyId=1225366058836607915, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.青岛海洋科学与技术试点国家实验室 海洋地质过程与环境功能实验室,山东 青岛 266237)])], figs=[ArticleFig(id=1225366062233993356, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 1, caption=Location of the study area and monitoring wells, figureFileSmall=75MmjItLhBww2ykAEpNrKg==, figureFileBig=xYEljGfcIFbn15NgMyEemg==, tableContent=null), ArticleFig(id=1225366062343045268, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图1, caption=研究区位置图及监测井分布, figureFileSmall=75MmjItLhBww2ykAEpNrKg==, figureFileBig=xYEljGfcIFbn15NgMyEemg==, tableContent=null), ArticleFig(id=1225366062460485791, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 2, caption=Time series of influencing factors

a. Precipitation; b. tide; c. evaporation; d. electricity consumption of agricultural irrigation and drainage

, figureFileSmall=cCbgxVBzEcJ/gLXgW7VnJg==, figureFileBig=xsMwJEZePX/ieDeZRcasFg==, tableContent=null), ArticleFig(id=1225366062556954787, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图2, caption=各影响因素时间序列

a. 降雨量;b. 潮汐;c. 蒸发量;d. 农业排灌用电量

, figureFileSmall=cCbgxVBzEcJ/gLXgW7VnJg==, figureFileBig=xsMwJEZePX/ieDeZRcasFg==, tableContent=null), ArticleFig(id=1225366062628257957, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 3, caption=Hydrogeology of the cross section from south to north in the study area (modified from reference [26])

1. Clay sand; 2. medium sand and gravel; 3. clay; 4. sandy clay; 5. bedrock; 6. groundwater level surface in 1992 (dash line) and 2013 (solid line)

, figureFileSmall=1yp9077kwxVOGt40/71Ehw==, figureFileBig=L8EBxPwAloSGxY9r70reGA==, tableContent=null), ArticleFig(id=1225366062716338347, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图3, caption=研究区剖面图(修改自文献[26])

1. 粉质黏土;2. 中砂及砾石;3. 黏土;4. 砂质黏土;5. 基岩;6 、1992年(虚线)和2013年(实线)地下水等势面

, figureFileSmall=1yp9077kwxVOGt40/71Ehw==, figureFileBig=L8EBxPwAloSGxY9r70reGA==, tableContent=null), ArticleFig(id=1225366062812807344, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 4, caption=Flow chart of WA-NARX neural network hybrid model

g(n) is low-pass filters; h(n) is high-pass filters; Ci is low-frequency approximations; Wi is high-frequency details

, figureFileSmall=GcQ9fyY5+HabVnnQGkdK/A==, figureFileBig=QYfCiMm3ymYy7AgKV6pMig==, tableContent=null), ArticleFig(id=1225366062921859249, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图4, caption=WA-NARX模型建模流程

g(n)为低通滤波器;h(n)为高通滤波器;Ci为近似分量;Wi为细节分量

, figureFileSmall=GcQ9fyY5+HabVnnQGkdK/A==, figureFileBig=QYfCiMm3ymYy7AgKV6pMig==, tableContent=null), ArticleFig(id=1225366063009939637, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 5, caption=Nonlinear auto-regression with exogenous input NARX, figureFileSmall=DmmEpI3DBMo+HjwmytEJ6g==, figureFileBig=v7mjb6znTIdmvlPqZR+VJg==, tableContent=null), ArticleFig(id=1225366063160934590, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图5, caption=输入到输出的NARX神经网络结构, figureFileSmall=DmmEpI3DBMo+HjwmytEJ6g==, figureFileBig=v7mjb6znTIdmvlPqZR+VJg==, tableContent=null), ArticleFig(id=1225366063244820672, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 6, caption=Groundwater level variation in monitoring wells from 2011 to 2012, figureFileSmall=2ah236mgNvdxp3fNMHqoCw==, figureFileBig=TasjPvnTE2MmudQzFeT+dA==, tableContent=null), ArticleFig(id=1225366063332901062, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图6, caption=监测井2011–2012年间地下水位变化曲线, figureFileSmall=2ah236mgNvdxp3fNMHqoCw==, figureFileBig=TasjPvnTE2MmudQzFeT+dA==, tableContent=null), ArticleFig(id=1225366063416787145, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 7, caption=Groundwater level and electrical conductivity variation in BH4 monitoring well, figureFileSmall=mIWa2yvDIWtNNB2YobO5qw==, figureFileBig=V/cAZWOfxcPcTTywgCcGIg==, tableContent=null), ArticleFig(id=1225366063509061838, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图7, caption=监测井BH4水位与电导率变化, figureFileSmall=mIWa2yvDIWtNNB2YobO5qw==, figureFileBig=V/cAZWOfxcPcTTywgCcGIg==, tableContent=null), ArticleFig(id=1225366063609725137, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 8, caption=Wavelet coherence analysis

a, b. Wavelet coherence between groundwater levels and tidal; c, d. wavelet coherence between electrical conductivity values and tidal

, figureFileSmall=W2G5bAL7834sHFnqG3LfVA==, figureFileBig=MfvJCr4Ezrh1+Sa54iN3qA==, tableContent=null), ArticleFig(id=1225366063697805528, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图8, caption=小波相干性分析

a, b. 地下水位与潮汐的相干性;c, d. 地下水电导率与潮汐的相干性

, figureFileSmall=W2G5bAL7834sHFnqG3LfVA==, figureFileBig=MfvJCr4Ezrh1+Sa54iN3qA==, tableContent=null), ArticleFig(id=1225366063832023261, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 9, caption=Comparison of groundwater level prediction based on WA-NARX and observation, figureFileSmall=GBhGK0/z/u0gIRdFAsjQxQ==, figureFileBig=WNM+hcpTLzB/1t+I5JZJhw==, tableContent=null), ArticleFig(id=1225366063932686561, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图9, caption=WA-NARX模型地下水位预测与观测对比, figureFileSmall=GBhGK0/z/u0gIRdFAsjQxQ==, figureFileBig=WNM+hcpTLzB/1t+I5JZJhw==, tableContent=null), ArticleFig(id=1225366064041738470, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 10, caption=Performance of WA-NARX model for electrical conductivity prediction, figureFileSmall=kWS4QT9aCTDzq9zOC8VXfw==, figureFileBig=Bgbz8tl6LKriokG/QCQoCA==, tableContent=null), ArticleFig(id=1225366064142401771, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图10, caption=WA-NARX模型电导率预测的性能图, figureFileSmall=kWS4QT9aCTDzq9zOC8VXfw==, figureFileBig=Bgbz8tl6LKriokG/QCQoCA==, tableContent=null), ArticleFig(id=1225366064268230895, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 11, caption=Scatter diagrams of predicted and observed groundwater level with newly added evaporation parameters, figureFileSmall=bJm7RJyhKC+cwKIo0NUSlA==, figureFileBig=CX4ee1e+iHk+af1m4XfmAA==, tableContent=null), ArticleFig(id=1225366064377282806, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图11, caption=新增蒸发参数的预测和实测地下水位散点图, figureFileSmall=bJm7RJyhKC+cwKIo0NUSlA==, figureFileBig=CX4ee1e+iHk+af1m4XfmAA==, tableContent=null), ArticleFig(id=1225366064477946104, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 12, caption=Scatter diagrams of predicted and observed groundwater level with newly added power consumption parameters, figureFileSmall=sakCkxDLB8ddhCvNVDeTQg==, figureFileBig=deHnIpA+Lt4nywOBmeUCFg==, tableContent=null), ArticleFig(id=1225366064591192315, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图12, caption=新增用电量参数的预测和实测地下水位散点图, figureFileSmall=sakCkxDLB8ddhCvNVDeTQg==, figureFileBig=deHnIpA+Lt4nywOBmeUCFg==, tableContent=null), ArticleFig(id=1225366064696049920, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 13, caption=Curve diagrams of predicted and observed electrical conductivity with newly added evaporation parameters, figureFileSmall=J6RjzNXmjYsgdb6H/fNH+g==, figureFileBig=qAuxgNXBtFvIuSDOt21vog==, tableContent=null), ArticleFig(id=1225366064813490438, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图13, caption=新增蒸发参数的预测和实测电导率曲线图, figureFileSmall=J6RjzNXmjYsgdb6H/fNH+g==, figureFileBig=qAuxgNXBtFvIuSDOt21vog==, tableContent=null), ArticleFig(id=1225366064939319562, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Fig. 14, caption=Curve diagrams of predicted and observed electrical conductivity with newly added power consumption parameters, figureFileSmall=9iKFfVZjlZgStBCgtZXl2Q==, figureFileBig=9AHjgeuXlyIKSaWyNz63YA==, tableContent=null), ArticleFig(id=1225366065056760077, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=图14, caption=新增用电量参数的预测和实测电导率曲线图, figureFileSmall=9iKFfVZjlZgStBCgtZXl2Q==, figureFileBig=9AHjgeuXlyIKSaWyNz63YA==, tableContent=null), ArticleFig(id=1225366065132257551, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Table 1, caption=

Analysis on statistical characteristics of groundwater level in monitoring wells (unit: m)

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井最大值最小值平均值标准差
BH11.451–0.8540.2700.422
BH22.681–0.2301.5040.633
BH34.092–0.2662.8650.516
BH46.3783.2305.0330.689
BH54.0142.1243.2590.403
BH64.3713.1963.7500.246
), ArticleFig(id=1225366065216143634, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=表1, caption=

监测井地下水位统计特征分析(单位:m)

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井最大值最小值平均值标准差
BH11.451–0.8540.2700.422
BH22.681–0.2301.5040.633
BH34.092–0.2662.8650.516
BH46.3783.2305.0330.689
BH54.0142.1243.2590.403
BH64.3713.1963.7500.246
), ArticleFig(id=1225366065291641110, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Table 2, caption=

Analysis on statistical characteristics of electrical conductivity in monitoring wells (unit: mS/cm)

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井最大值最小值平均值标准差标准离散率
BH12.080.631.220.50541.39%
BH21.691.531.650.021 1.27%
BH31.621.011.200.12110.08%
BH413.172.394.702.25247.91%
BH516.953.688.953.19635.71%
BH615.324.126.613.14347.55%
), ArticleFig(id=1225366065396498714, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=表2, caption=

监测井电导率统计特征分析(单位:mS/cm)

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井最大值最小值平均值标准差标准离散率
BH12.080.631.220.50541.39%
BH21.691.531.650.021 1.27%
BH31.621.011.200.12110.08%
BH413.172.394.702.25247.91%
BH516.953.688.953.19635.71%
BH615.324.126.613.14347.55%
), ArticleFig(id=1225366065492967709, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Table 3, caption=

The WA-NARX model performance metrics of RMSE and R2 for groundwater level prediction

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井训练数据测试数据
RMSER2RMSER2
BH10.004 10.999 9 0.003 90.999 8
BH20.004 21.000 0 0.004 30.999 9
BH30.028 10.997 1 0.014 70.998 3
BH40.004 90.999 9 0.005 40.999 9
BH50.003 00.999 9 0.006 00.999 6
BH60.003 40.999 8 0.003 90.998 7
), ArticleFig(id=1225366065597825312, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=表3, caption=

地下水位预测时WA-NARX模型的均方根误差(RMSE)和拟合度(R2)统计表

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井训练数据测试数据
RMSER2RMSER2
BH10.004 10.999 9 0.003 90.999 8
BH20.004 21.000 0 0.004 30.999 9
BH30.028 10.997 1 0.014 70.998 3
BH40.004 90.999 9 0.005 40.999 9
BH50.003 00.999 9 0.006 00.999 6
BH60.003 40.999 8 0.003 90.998 7
), ArticleFig(id=1225366065732043047, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Table 4, caption=

The WA-NARX model performance metrics of RMSE and R2 for electrical conductivity prediction

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井训练数据测试数据
RMSER2RMSER2
BH10.001 31.000 0 0.001 50.999 4
BH20.000 780.998 5 0.000 890.989 7
BH30.005 10.998 4 0.005 00.993 6
BH40.007 41.000 0 0.005 30.999 5
BH50.003 91.000 0 0.002 60.990 5
BH60.008 51.000 0 0.004 40.997 8
), ArticleFig(id=1225366065832706346, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=表4, caption=

电导率预测时WA-NARX模型的均方根误差(RMSE)和拟合度($ {{R}}^{2} $)统计

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井训练数据测试数据
RMSER2RMSER2
BH10.001 31.000 0 0.001 50.999 4
BH20.000 780.998 5 0.000 890.989 7
BH30.005 10.998 4 0.005 00.993 6
BH40.007 41.000 0 0.005 30.999 5
BH50.003 91.000 0 0.002 60.990 5
BH60.008 51.000 0 0.004 40.997 8
), ArticleFig(id=1225366065916592430, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Table 5, caption=

The prediction error of groundwater level and network performance with newly added evaporation parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井输入降雨、潮汐参数输入降雨、潮汐、蒸发参数
网络性能RMSER2网络性能RMSER2
BH11.619 3×10–50.004 00.957 1 1.526 1×10–50.004 40.948 4
BH22.569 7×10–50.005 10.961 9 3.006 6×10–50.005 50.955 4
BH38.991 8×10–50.009 50.935 7 7.640 4×10–50.008 70.945 4
BH42.476 8×10–50.009 80.880 7 9.752 6×10–50.009 90.878 5
BH52.381 2×10–40.015 40.643 7 5.149 2×10–40.022 70.229 5
BH61.392 0×10–50.003 70.983 9 1.249 7×10–50.003 50.985 5
), ArticleFig(id=1225366066021450034, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=表5, caption=

新增蒸发参数的地下水位预测误差及网络性能统计表

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井输入降雨、潮汐参数输入降雨、潮汐、蒸发参数
网络性能RMSER2网络性能RMSER2
BH11.619 3×10–50.004 00.957 1 1.526 1×10–50.004 40.948 4
BH22.569 7×10–50.005 10.961 9 3.006 6×10–50.005 50.955 4
BH38.991 8×10–50.009 50.935 7 7.640 4×10–50.008 70.945 4
BH42.476 8×10–50.009 80.880 7 9.752 6×10–50.009 90.878 5
BH52.381 2×10–40.015 40.643 7 5.149 2×10–40.022 70.229 5
BH61.392 0×10–50.003 70.983 9 1.249 7×10–50.003 50.985 5
), ArticleFig(id=1225366066092753206, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Table 6, caption=

The prediction error of groundwater level and network performance with newly added power consumption parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井输入降雨、潮汐参数输入降雨、潮汐、用电量参数
网络性能RMSER2网络性能RMSER2
BH11.619 3×10–50.004 00.957 1 2.216 3×10–50.004 70.941 3
BH22.569 7×10–50.005 10.961 9 7.072 1×10–50.008 40.895 0
BH38.991 8×10–50.009 50.935 7 2.027 0×10–40.014 20.855 1
BH42.476 8×10–50.009 80.880 7 2.743 9×10–40.016 60.658 0
BH52.381 2×10–40.015 40.643 7 1.064 5×10–40.010 30.840 7
BH61.392 0×10–50.003 70.983 9 1.236 6×10–50.003 50.985 7
), ArticleFig(id=1225366066159862076, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=表6, caption=

新增用电量参数的地下水位预测误差及网络性能统计

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井输入降雨、潮汐参数输入降雨、潮汐、用电量参数
网络性能RMSER2网络性能RMSER2
BH11.619 3×10–50.004 00.957 1 2.216 3×10–50.004 70.941 3
BH22.569 7×10–50.005 10.961 9 7.072 1×10–50.008 40.895 0
BH38.991 8×10–50.009 50.935 7 2.027 0×10–40.014 20.855 1
BH42.476 8×10–50.009 80.880 7 2.743 9×10–40.016 60.658 0
BH52.381 2×10–40.015 40.643 7 1.064 5×10–40.010 30.840 7
BH61.392 0×10–50.003 70.983 9 1.236 6×10–50.003 50.985 7
), ArticleFig(id=1225366066298274113, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=EN, label=Table 7, caption=

The prediction error of electrical conductivity and network performance with different input parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井输入降雨、潮汐参数输入降雨、潮汐、蒸发参数输入降雨、潮汐、用电量参数
网络性能RMSE网络性能RMSE网络性能RMSE
BH12.005 4×10–50.004 5 7.984 9×10–60.002 8 1.383 1×10–50.003 7
BH21.086 4×10–70.000 33 1.086 0×10–70.000 30 4.927 2×10–80.000 31
BH31.409 1×10–60.001 2 4.998 2×10–70.000 71 1.637 8×10–60.001 3
BH41.072 6×10–50.003 3 1.946 0×10–50.004 4 1.368 7×10–50.003 7
BH51.100 0×10–30.033 9 3.371 9×10–40.005 8 5.466 2×10–40.023 4
BH61.136 3×10–50.003 4 1.161 5×10–50.003 4 1.007 5×10–50.003 2
), ArticleFig(id=1225366066386354502, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1224795176200192232, language=CN, label=表7, caption=

不同输入参数电导率预测误差及网络性能评价统计

, figureFileSmall=null, figureFileBig=null, tableContent=
监测井输入降雨、潮汐参数输入降雨、潮汐、蒸发参数输入降雨、潮汐、用电量参数
网络性能RMSE网络性能RMSE网络性能RMSE
BH12.005 4×10–50.004 5 7.984 9×10–60.002 8 1.383 1×10–50.003 7
BH21.086 4×10–70.000 33 1.086 0×10–70.000 30 4.927 2×10–80.000 31
BH31.409 1×10–60.001 2 4.998 2×10–70.000 71 1.637 8×10–60.001 3
BH41.072 6×10–50.003 3 1.946 0×10–50.004 4 1.368 7×10–50.003 7
BH51.100 0×10–30.033 9 3.371 9×10–40.005 8 5.466 2×10–40.023 4
BH61.136 3×10–50.003 4 1.161 5×10–50.003 4 1.007 5×10–50.003 2
)], attaches=null, journal=Journal(id=1146441459026210850, delFlag=0, nameCn=海洋学报, nameEn=Haiyang Xuebao, nameHistory1=null, nameHistory2=null, issn=0253-4193, eissn=null, cn=11-2055/P, coden=null, periodic=0, language=CN, oaType=否, 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=uYi7hkkrve+l8pIcwqcaQQ==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1751262543687, updatedTime=1761729782936, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=H, firstLetterEn=H, subjectCode=Natural Sciences, subjectName=Natural Sciences, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=uYi7hkkrve+l8pIcwqcaQQ==, picEn=C0WLQb7uW3ok8EkkVOAGuw==, jcr=null, cjcr=null, exts=[JournalExt(id=1190344242636624294, language=CN, name=海洋学报, 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=http://www.hyxbocean.cn/, createdTime=1761729782971, updatedTime=1761729782971, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.hyxb.org.cn/aos/ch/author/login.aspx, submissionEditorUrl=http://www.hyxb.org.cn/aos/ch/login.aspx, submissionReviewUrl=http://www.hyxb.org.cn/aos/ch/auditor/login.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190344242712121767, language=EN, name=Haiyang Xuebao, 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=http://www.aosocean.com/, createdTime=1761729782989, updatedTime=1761729782989, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.hyxb.org.cn/aos/ch/author/login.aspx, submissionEditorUrl=http://www.hyxb.org.cn/aos/ch/login.aspx, submissionReviewUrl=http://www.hyxb.org.cn/aos/ch/auditor/login.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1149651085930835976, websiteList=[Website(id=1188165202219512001, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1149651085930835976, 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/hyxb/CN, language=CN, createTime=1761210259251, createBy=18614031015, updateTime=1761210330879, updateBy=18614031015, name=海洋学报-中文, tplId=1146099689490845704, title=海洋学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1188166688563413602, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=articleTextType, value=kx, createTime=1761210613623, updateTime=1761210613623, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688538247775, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=banner, value=null, createTime=1761210613617, updateTime=1761210613617, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688529859166, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=logo, value=https://castjournals.cast.org.cn/joweb/hyxb/CN/file/pic?fileId=BDEio/cxHnid8OD4QxrAYQ==, createTime=1761210613615, updateTime=1761210613615, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688555024993, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/hyxb/CN/file/pic, createTime=1761210613621, updateTime=1761210613621, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688546636384, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761210613619, updateTime=1761210613619, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688575996515, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=themeColor, value=null, createTime=1761210613626, updateTime=1761210613626, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688596968036, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=themeStyle, value=null, createTime=1761210613631, updateTime=1761210613631, creator=18614031015, updator=18614031015)]), Website(id=1188165202282426564, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1149651085930835976, 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/hyxb/EN, language=EN, createTime=1761210259266, createBy=18614031015, updateTime=1761210377920, updateBy=18614031015, name=海洋学报-英文, tplId=1146101810881728533, title=Haiyang Xuebao, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1188166798101856873, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=articleTextType, value=kx, createTime=1761210639739, updateTime=1761210639739, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798076691046, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=banner, value=null, createTime=1761210639733, updateTime=1761210639733, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798068302437, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=logo, value=https://castjournals.cast.org.cn/joweb/hyxb/EN/file/pic?fileId=BDEio/cxHnid8OD4QxrAYQ==, createTime=1761210639731, updateTime=1761210639731, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798093468264, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/hyxb/EN/file/pic, createTime=1761210639737, updateTime=1761210639737, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798085079655, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761210639735, updateTime=1761210639735, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798106051178, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=themeColor, value=null, createTime=1761210639740, updateTime=1761210639740, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798110245483, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=themeStyle, value=null, createTime=1761210639741, updateTime=1761210639741, creator=18614031015, updator=18614031015)])], journalTitle=海洋学报, weixinUrl=null, journalUrl=http://www.hyxbocean.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Haiyang Xuebao, journalPhotoCn=uYi7hkkrve+l8pIcwqcaQQ==, journalPhotoEn=C0WLQb7uW3ok8EkkVOAGuw==, journalFirstLetter=H, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/hyxb/CN/10.12284/hyxb2022015, detailUrlEn=https://castjournals.cast.org.cn/joweb/hyxb/EN/10.12284/hyxb2022015, pdfUrlCn=https://castjournals.cast.org.cn/joweb/hyxb/CN/PDF/10.12284/hyxb2022015, pdfUrlEn=https://castjournals.cast.org.cn/joweb/hyxb/EN/PDF/10.12284/hyxb2022015, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
莱州湾南岸海水入侵特征及基于WA-NARX混合模型的动态预测
收藏切换
PDF下载
董凡 1, 2 , 张晓影 1, * , 陈广泉 2, 3, * , 戴振学 1 , 王延诚 2, 3
海洋学报 | 论文 2022,44(3): 81-97
收起
收藏切换
海洋学报 | 论文 2022, 44(3): 81-97
莱州湾南岸海水入侵特征及基于WA-NARX混合模型的动态预测
全屏
董凡1, 2 , 张晓影1, * , 陈广泉2, 3, * , 戴振学1, 王延诚2, 3
作者信息
  • 1.吉林大学 建设工程学院,吉林 长春 130026
  • 2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061
  • 3.青岛海洋科学与技术试点国家实验室 海洋地质过程与环境功能实验室,山东 青岛 266237
  • 董凡(1997—),男,陕西省商洛市人,主要从事基于深度学习的地下水位预测研究。E-mail:

通讯作者:

张晓影,女,副教授,博士生导师,主要从事非均质介质中溶质反应迁移模拟及尺度效应研究。E-mail:
陈广泉,男,高级工程师,主要从事海洋地质与海水入侵研究。E-mail:
Seawater intrusion characterization and dynamics prediction based on WA-NARX hybrid model in the south of Laizhou Bay
Fan Dong1, 2 , Xiaoying Zhang1, * , Guangquan Chen2, 3, * , Zhenxue Dai1, Yancheng Wang2, 3
Affiliations
  • 1. College of Construction Engineering, Jilin University, Changchun 130026, China
  • 2. Key Laboratory of Coastal Science and Integrated Management, First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China
  • 3. Laboratory for Marine Geology, Pilot National Laboratory for Marine Science and Technology (Qingdao), Qingdao 266237, China
出版时间: 2022-03-01 doi: 10.12284/hyxb2022015
文章导航
收藏切换

随着我国海岸带经济的快速发展与人类活动的加剧,地下水超采现象十分严峻,由此引发的海水入侵已成为滨海地区普遍存在的地质问题。本研究以莱州湾南岸海水入侵区为研究对象,根据地下水连续监测数据分析了地下水位和电导率的动态变化特征。在此基础上,基于降雨、蒸发、潮汐及农业排灌用电量等影响地下水动态变化的因素,建立了小波分析(WA)与具有外部输入的非线性自回归神经网络(NARX)的混合模型,对地下水水位和电导率进行动态预测,并采用均方根误差和拟合度对预测结果进行评价。研究结果表明,莱州湾南岸地下水年内动态变化特征为降雨入渗–开采型,地下水位和潮汐之间在0.5 d频率上呈现较高相关性,潮汐对地下水电导率的影响要弱于对地下水位的影响;WA-NARX混合模型在训练和测试阶段的均方根误差均小于0.03且拟合度大于0.98,可有效预测研究区海水入侵的变化程度。同时,为验证模型适用性,对比了不同影响因素作为模型输入参数对预测结果的影响。结果表明,降雨和潮汐参数是影响海岸带地下水位和电导率的主要变量,蒸发以及农业排灌用电量反映的部分抽水信息对地下水位和电导率也有影响,其影响程度与观测频率相关。本文研究结果可为海岸带海水入侵的实时监测、预测、预警提供理论与技术支撑。

海水入侵  /  地下水水位  /  电导率  /  小波分析  /  NARX神经网络  /  预测

With the rapid economic development and increasing anthropogenic activities, the groundwater in the coastal area has been excessively exploited. The resulting seawater intrusion has become a widely distributed environmental geological problem. Taken the coastal area of Laizhou Bay as a research area, the dynamics of groundwater level (GWL) and electrical conductivity (EC) were analyzed with the continuous monitoring data. Based on the rainfall, evaporation, tide and agricultural irrigation and drainage electricity consumption that affect the groundwater variation, the hybrid model of wavelet analysis (WA) and NARX neural network was introduced to predict the dynamics of GWL and EC. The root mean square error (RMSE) and goodness of fit (R2) were used to measure the prediction accuracy. The results showed that the annual variation of GWL was characterized by a type of rainfall infiltration-exploitation. A significant correlation at the frequency of 0.5 d was observed between groundwater level and tide, and the influence of tide on EC was weaker than that on GWL. For the dynamics prediction with WA-NARX method, the RMSE was less than 0.03 and R2 was greater than 0.98 in both the training and testing stages. The results indicated the hybrid model had a good performance and could effectively predict the dynamics of GWL and EC. The effects of different influencing factors as model input parameters on the prediction results were further compared. The results showed that rainfall and tide parameters were the main variables affecting the GWL and EC variations in the coastal zone. The pumping information reflected by the evaporation and agricultural drainage and irrigation power consumption also affected the groundwater dynamics. The degree of influence was related to the observation frequency. The research results can provide theoretical and technical support for real-time monitoring, prediction and early warning of seawater intrusion in coastal zone.

seawater intrusion  /  groundwater level  /  electrical conductivity  /  wavelet analysis  /  NARX neural network  /  prediction
董凡, 张晓影, 陈广泉, 戴振学, 王延诚. 莱州湾南岸海水入侵特征及基于WA-NARX混合模型的动态预测. 海洋学报, 2022 , 44 (3) : 81 -97 . DOI: 10.12284/hyxb2022015
Fan Dong, Xiaoying Zhang, Guangquan Chen, Zhenxue Dai, Yancheng Wang. Seawater intrusion characterization and dynamics prediction based on WA-NARX hybrid model in the south of Laizhou Bay[J]. Haiyang Xuebao, 2022 , 44 (3) : 81 -97 . DOI: 10.12284/hyxb2022015
近年来,受气候变化和人类活动的双重影响,全球海岸地区都面临着海水入侵的威胁。海水入侵可引发地下水水质恶化、土壤退化等生态环境问题,严重制约社会的可持续发展[1-4]。科学管理沿海地区地下水,预测近岸地下水位和电导率,掌握地下水位及盐度的动态变化,对合理开发利用海岸带地下水资源,防止海水入侵加剧,保护海岸带生态环境有十分重要的指导意义。然而,受自然条件和人为因素的影响,海水入侵在时间序列上表现出时空性、不确定性及动态变化等特性,多种因素对海水入侵的影响并非多因子影响的线性叠加,从而使预测海水入侵的演化过程变得十分困难。
随着人工智能的兴起,由于人工神经网络(ANN)可以较好地映射非线性变化,因此被广泛应用在水文变量预测中。其中BP神经网络模型的应用范围最广[5],但其神经网络训练的时间长,收敛速度慢,输入信号由输入层单向传递给输出层,网络模型只能使用有限步的历史信息。而循环神经网络(RNN)凭借其循环结构的特点,通过反馈连接可以使用长期的历史信息,因此更加适合时间序列的预测[6]。具有外部输入的非线性自回归神经网络(Nonlinear Autoregressive Models with Exogenous Inputs,NARX)作为循环神经网络的一种,在地下水位的预测研究领域备受青睐。Guzman 等[7]使用NARX模型预测密西西比河流域含水层,Wunsch等[8]运用NARX模型预测德国西南部数口井的地下水水位,Di Nunno和Granata[9]应用NARX网络预测位于普利亚地区的76口监测井的日地下水水位。研究结果表明,NARX神经网络在预测时间序列上具有显著优势。
尽管ANN在时间序列预测方面应用广泛,具有灵活性,但是如果不对输入和输出数据进行预处理,它可能无法处理非平稳数据[10-11]。小波变换作为一种数据预处理技术,可以将非平稳时间序列的小波分解成不同的尺度,提供对序列结构的解释,并仅用几个系数来提取有关其历史的重要信息。该技术被广泛应用于非平稳信号的时间序列分析[12],通过将非平稳信号分解成不同时间水平的子信号,可以较好地预测非平稳信号[13-18]。将小波变换和人工神经网络模型相结合,发挥这两种模型的优势,可以明显提高预测精度,增加有效预测时段。目前,混合模型已广泛应用于部分水文要素的预测,如降雨、径流和蒸发[19]。张建峰等[20]建立小波–BP神经网络的混合模型预测华北平原城市地下水位。Seo等[21]将小波分析(WA)分别结合BP神经网络、自适应神经模糊推理系统,预测水库水位并对结果进行对比。Zhang等[22]构建了小波分析和NARX神经网络混合模型对舟山填海区地下水位进行预测,预测精度较高。
由于受全新世海侵、气候干旱、海平面上升以及不合理的人类活动的影响,莱州湾地区是我国海水入侵灾害最为严重和典型的地区[23]。近年来,在上述因素综合影响下,莱州湾地区地下咸水体分布面积已超过22 000 km2[24],严重污染地下淡水资源,土壤次生盐渍化面积不断扩大,对海岸带区域的工农业生产和生态环境造成严重影响,海水入侵已成为该地区严重的环境问题之一,严重制约经济社会发展。因此,开展莱州湾地区海水入侵动态特征分析,建立预测模型,对提高海岸带地区防灾减灾能力和经济、社会可持续发展具有重要意义。在本研究选择莱州湾南岸典型监测剖面,首先分析地下水位和地下水电导率的动态变化特征,分析对比不同输入参数对模型预测精度的影响,建立基于WA-NARX混合的海水入侵预测模型,对近岸地下水位和电导率进行预测模拟,研究结果可为海岸带海水入侵的实时监测、预测、预警提供理论与技术支撑。
研究区位于莱州湾南部(图1),潍坊北部的滨海区。研究区内设有6口监测井(BH01–BH06),分别沿垂直于海岸带的剖面由靠近海岸带的监测井BH06向内陆的监测井BH01方向分布。研究收集了降雨、蒸发、潮汐、电导率、地下水位和农业排灌用电量数据,见图2。其中,潮汐的变化是潮位站监测的海水位每小时的变化,降雨量与蒸发量是日测数据,排灌用电量是研究区每小时灌溉所用电量。研究选取2011年10月1日至2012年10月31之间的监测数据作为研究对象。
莱州湾南岸地区属于鲁北平原水文地质区、潍北滨海平原水文地质亚区。该地区地表水系较发达,地下水水文地质特征在水平和垂向上均变化明显。地貌类型由南向北依次为山前冲洪积平原、冲积海积平原和滨海海积平原,海岸类型为粉砂淤泥质海岸。此处的冲洪积平原由多个扇缘相互交接的冲洪积扇群组成,冲洪积平原的前缘被海积物或黄河冲积物所掩埋,含水层厚度大、颗粒粗,具有多层结构。含水层颗粒自上而下呈现由粗变细的趋势,而在水平方向上则具有冲洪积扇的水文地质特征[25]
如图3所示,研究区普遍存在一层中更新统砂质黏土弱透水层,埋深一般为 40~70 m,层厚约20 m。有3层海侵层,分别对应晚更新世以来发生的3次大海侵。在3次海侵中都滞留了浓缩于地层中的古海水(咸–卤水),与淡水含水层在水平方向上相连,是该区咸–卤水入侵的来源,主要出现在晚更新世和全新世地层中。
在本研究中,运用小波分析的方法来识别显著的振荡周期,从原始数据中提取有用的信息,并将这些信息分解成一系列小波函数,小波函数由母波函数生成。本文采用的母波函数是Morlet小波:
$ {\text{ψ}}({t})={\text π}^{-1/4}{\mathrm{e}}^{{iw}_{0}{t}}{\mathrm{e}}^{{-{t}}^{2}/2}, $
式中,w0为无量纲频率;t为时间。通常,选择w0=6的Morlet小波[27-28]。连续小波变换(CWT)用于识别信号在时频域的主振荡。连续小波变换的f(t)如下所示:
$ {W}\left({a},{b}\right)={\left|{a}\right|}^{-\frac{1}{2}}{\int }_{-{\infty }}^{+{\infty }}{f}\left({t}\right)\bar{\text{ψ}}\left(\dfrac{{t}-{b}}{{a}}\right)\mathrm{d}{t} \text{,} $
式中,a为尺度或频率参数;b为时间或位移参数;$\bar{\text{ψ}}\left({t}\right)$是复共轭函数${\text{ψ}}({t})$。由式(2)可知,小波变换在不同分辨率或尺度下呈现出不规则和不对称的特点,将f(t)分解为一系列低分辨率分量。
在实际应用中,连续小波变换常被离散小波变换(DWT)所代替。令$ {a}={{a}}_{0}^{{j}} $, $ {b}={k}{{b}}_{0}{{a}}_{0}^{{j}} $, $ {{a}}_{0} > 1 $, $ {{b}}_{0}\in {R} $, kj为整数,则f(t)的离散小波变换可表示为
$ {W}\left({j},{k}\right)={{a}}_{0}^{-\frac{{j}}{2}}{\int }_{-{\infty }}^{+{\infty }}{f}\left({t}\right)\bar{\text{ψ}}({{a}}_{0}^{-{j}}{t}-{k}{{b}}_{0})\mathrm{d}{t} . $
在式(3)中,参数a0b0最常用的选择是使用对数缩放[29],即$ {{a}}_{0}=2 $, $ {{b}}_{0}=1 $。原始时间序列在频率(aj)和时间(bk)域的特征被连续小波变换的W(a, b)或离散小波变换的W(j, k)所反映。
将经典的连续小波转换为离散小波有多种算法,如Mallat算法和á Trous算法。本文采用了á Trous算法[30]。á Trous的分解算法定义如下:
${{{C}}_{{i}}}\left( {{t}} \right) = \sum\limits_{{{n}} = - \infty }^{ + \infty } {{{g}}\left( {{n}} \right){{{C}}_{{{i}} - 1}}({{t}} + {2^{{i}}}{{n}})} \;\;\;({{i}} = {{1}},{{2}}, \cdots ), $
$ {{W}}_{{i}}\left({t}\right)={{C}}_{{i}-1}\left({t}\right)-{{C}}_{{i}}\left({t}\right) \;\;\; ({i}={1,2},\cdots ), $
式中,g(n)为离散低通滤波器;$ {{C}}_{{i}}\left({t}\right) $和$ {{W}}_{{i}}\left({t}\right) $ $({i}= {1,2},\cdots )$分别是分辨率为i级的尺度系数和小波系数。$ {{W}}_{1}\left({t}\right) $,$ {{W}}_{2}\left({t}\right) $,···,$ {{W}}_{{p}}\left({t}\right) $ 和 $ {{C}}_{{p}}\left({t}\right) $组成分辨率为P的离散小波变换。
在小波分析中经常使用近似特征和细节分量,近似特征表示信号的低尺度,即低频信息;细节分量表示信号的高尺度,即高频信息。离散小波变换使用低通滤波器g(n)和高通滤波器h(n)将f(t)分解成不同尺度上的低频成分($ {{C}}_{1} $,$ {{C}}_{2} $,$ {{C}}_{3} \cdots$)和高频成分($ {{W}}_{1} $,$ {{W}}_{2} $,$ {{W}}_{3} \cdots$)。因此,f(t)可以分解为包含其近似分量(低频成分)和细节分量(高频成分)。高频信号捕获原始时间序列数据中的小尺度特征,见图4小波分解部分。
NARX神经网络是一种有外部输入的非线性自回归网络模型[31],表示为
$\begin{split} y(t)=&f[y(t-1),y(t-2),\cdots,y(t-{n}_{y}),x(t-1),\\&x(t-2),\cdots,x(t-{n}_{u})] \text{,} \end{split}$
式中,y(t)代表输出信号;x(t)代表外部输入信号;f为非线性函数。即输出信号y(t)可由输出信号前ny个值和外部输入信号x(t)前nu个值通过f非线性映射得到。
NARX神经网络由网络的输出反馈和动态的神经元构成,是一种动态神经网络。它的结构清晰,通常包含输入层、输出层、隐含层及输入延时和输出延时这些网络结构(图5)。NARX神经网络具有开环和闭环两种模式,闭环网络可以进行多步预测。与一般神经网络相比,NARX 神经网络的反馈结构和梯度下降算法使其拥有更好的收敛速度和学习效率,是一种研究较为广泛的动态神经网络[32-33],因此,NARX神经网络既可以用于时间序列建模,也可以用于非线性滤波[34]
WA-NARX混合模型是利用多分辨率小波分解得到的子时间序列作为输入的NARX模型。利用小波变换将原始信号依次分解成不同尺度上的信号成分,á Trous算法产生低频的近似分量(C)和高频的细节分量(W [35]。本研究利用${L}=\mathrm{int}\left[{\mathrm{lg}}\left({n}\right)\right]$来确定小波的分解层数[36],其中L表示小波层的个数,n表示时间序列中的数据点个数,int[ ]为取整函数。研究所包含时间序列的数据点个数为9 528,经计算需要4个分辨率级别。
本研究中,利用á Trous算法首先将水位、潮汐和降雨等参数的小时时间序列分解为一定数量的子时间分量。根据潮汐水位随时间的变化规律,运用小波分析的方法来识别显著的振荡周期,并从原始数据中提取潮汐水位变化的近似特征值和细节分量,然后将时间分量作为混合模型的输入。选择最重要的时间分量作为输入,这些时间分量与原始数据具有很高的相关性。为了判别预测的准确性,本文将均方根误差(RMSE)和拟合度($ {{R}}^{2} $)作为性能指标来衡量模型的预测精度。同时,利用matlab中的perform函数结合网络结构与均方误差(MSE)计算网络性能来评价网络的学习及预测能力。
WA-NARX混合模型在建模过程中,数据被分为两个子集:训练集和测试集。训练数据集(75%)用于优化网络配置,测试数据集(25%)用于测试网络性能。此外,WA-NARX混合模型的隐含层神经元数是通过反复试验确定的。在本次研究中,最终确定10个隐含层神经元。WA-NARX模型建模流程见图4,如图所示:首先是参数和样本的选择,利用小波变换将原始时间序列分解成不同信号成分的小波分量,然后将分解的小波分量输入到NARX神经网络模型中进行训练预测,最终得到预测结果。
根据研究区监测井2011–2012年间的地下水水位监测数据,结合研究区内相应时段的降雨量绘制监测点的地下水位动态变化曲线(图6)。根据研究区2011–2012年各监测井采集的地下水位动态数据,计算各监测井地下水位的最大值、最小值、平均值以及标准差等空间变化统计特征,计算结果见表1图6显示,各监测井地下水位的变化趋势基本一致。监测井在2011–2012年间的地下水位的变幅为1.175~4.358 m,各监测井地下水位在2011年12月、2012年4月、2012年8月这3个时间段内均有突变点,与降雨量变化相对应。在降雨后,多数监测井地下水位有明显上升的趋势。2011年的11月份到2012年的2月份水位逐渐上升后趋于平缓,因降雨补给存在滞后效应,随后水位开始下降,2012年3–4月份水位随着降雨上升,在4月末水位达到全年最高值,因春灌开采影响,5月份虽有降雨补给,但地下水位也开始下降,7–8月是降雨最频繁月份,受强降雨的影响,地下水位随降雨量波动变化。在降雨过程中,间歇性的小雨只能湿润土壤表层,不能有效补给地下水;集中式暴雨入渗系数低,大部分转化为地表径流。而连续小雨可以充分入渗到地下,因此有利于地下水补给[37]。可以判断监测井2011–2012年地下水年内动态变化特征为降雨入渗–开采型。
地下水超采是海水入侵最直接的原因,地下水位的持续下降会破坏水压力平衡,当沿海含水层地下水位低于海平面时,就会发生海水入侵,因此在分析区域内海水入侵状况时,可以根据地下水位的动态变化近似推断海水入侵状况。对海水入侵的监测,通常是对地下水中氯化物和矿化度进行分析[38],也有相关研究[39-40]用电导率替代Cl作为监测海水入侵的指标,指出水中Cl含量与电导率成正比。如图7所示,地下水位和电导率在一定程度上呈负相关,即地下水位下降,电导率上升。当地下水位下降时,淡水入海流量减小,海水入侵加剧,地下水中电导率升高。因此,从图中可以看出地下水位动态变化特征在年内时间尺度可较为准确表征海水入侵的变化。
根据研究区2011–2012年各监测井采集的电导率动态数据,计算各监测井电导率的最大值、最小值、平均值、标准差以及标准离散率等空间变化统计特征,结果见表2
标准离散率θ 的计算公式为
$ \theta =\dfrac{{S}_{D}}{\overline{K}}\times 100{\text \%}, $
式中,$ {S}_{D} $为电导率的标准差;$ \overline{K} $为电导率的平均值。
温度为20℃时,天然水的电导率介于0.5~1.5 mS/cm。在滨海地区,电导率可以作为一项评判海水入侵的指标,电导率的值越小说明地下水受海水入侵程度越低[41-42]。由上表可以得出,监测井BH1、BH2和BH3的电导率值大致在天然水电导率的范围附近,没有出现电导率异常现象,因此这几口监测井的地下水基本未受海水入侵的影响;而BH4、BH5及BH6的电导率值远超出该范围,说明地下水在很大程度上受到海水入侵的影响。
从电导率的平均值来看,BH5的值最高,水质相对较差,其主要原因可能与该处的地下水开采所导致的海水入侵有关,距离它较近的BH4和BH6的值也较高;BH3的平均电导率最低,为1.20 mS/cm,说明此处的地下水质相对较好。监测井BH4的标准离散率最高,为47.91%,说明该点地下水电导率相差较大;BH2的标准离散率最低,为1.27%,说明该点的电导率的稳定性较高。
为了理解潮汐对地下水位和地下水电导率的影响,引入小波相干性识别潮汐与地下水位和电导率之间的统计关系。潮汐与地下水位和电导率之间的小波相干性分析结果如图8所示(图中以监测井BH2和BH6为例),谱之间的相位关系用箭头的方向表示。影响锥(白色虚线)表示小波谱的区域,在该区域由于基础数据的有限长度特性而产生的边缘效应不能被忽略。
(1)地下水位和潮汐之间的小波相干性分析
小波相干性分析结果表明,每口监测井的地下水位与潮汐数据之间存在不同的相干性。监测井BH2和BH6,在整个时间序列中频谱值有相应变化(图8a图8b),这些频率代表地下水位对潮汐变化的响应。对于监测井BH2和BH6,地下水位和潮汐在0.25 d频率上的相干性很小,0.5 d相干性较高,1 d的相干性相对较弱,但相关分布在不同时间是间歇性的。在0.5 d周期内,与监测井BH6同期地下水位和潮汐资料相比,监测井BH2中的地下水位对潮汐的响应时间不同,相干性更弱,这可能与BH2的位置及地质条件有关。小波相干性分析表明,海岸带含水层的地下水位受到海洋潮汐变化的影响。潮汐信号对地下水位的影响具有时空差异。靠近海岸的地区更容易受潮汐影响。同时,某些地区的潮汐效应一般与它们相对于海洋的位置和地质条件的综合效应相关[43]
(2)地下水电导率和潮汐之间的小波相干性分析
图8c图8d显示,将小波相干性分析应用于监测的地下水电导率数据和潮位时间序列时,未检测到连续的短期时间相关性。监测井BH2在2012年7月1日至2012年10月1日时间段内电导率和潮汐之间存在16~32 d的长周期相关性。监测井BH6中电导率和潮汐之间存在短期的相关性,可以看出不同井位的电导率对潮汐变化的响应不同。潮汐对地下水电导率的影响要弱于对地下水位的影响,因为地下水位的波动是受应力变化的影响,而电导率的变化需要含水层储水量的体积变化。更重要的是,地质条件对控制潮汐对地下水位的影响至关重要。
WA-NARX神经网络混合模型在NARX神经网络模型的基础上,引入小波分析,对数据进行小波分解以减小预测误差,提高预测精度。在进行海岸带地下水位预测时,把降雨和潮汐作为输入参数,经WA-NARX混合模型模拟得到地下水位预测结果,同水位的观测值进行对比,得到预测结果的散点图和时间序列图。图9显示了BH1–BH6这6口监测井地下水位的预测结果。
图9a图9c图9e图9g图9i图9k为预测结果散点图,图9b图9d图9f图9h图9j图9l为预测结果时间序列图。通过预测结果散点图可得:训练数据和预测数据集中分布一条直线上,模型在水位变幅较大时预测效果有所降低。如图所示,监测井BH3的散点出现小幅度的偏离。通过预测结果的时间序列图可得:训练和测试过程水位变化趋势与观测水位变化趋势一致。混合模型在训练和测试过程中均表现出较低的误差,在地下水位波动处误差相对较高,但模型总体上表现出良好的模拟效果。WA-NARX神经网络混合模型在训练阶段和测试阶段的RMSE和$ {{R}}^{2} $性能指标值见表3,从表3可见,所有监测井在训练和测试阶段的$ {{R}}^{2} $均大于0.99, RMSE均小于0.03,表明模型性能良好。
BH1–BH6 6口监测井电导率的预测结果散点图和时间序列图如图10所示,从混合模型模拟结果可以看出:混合模型的训练数据和测试数据基本集中分布在一条直线上,电导率的变化趋势与观测电导率的变化趋势一致,在训练和测试阶段模型的误差都相对较低。因此WA-NARX神经网络混合模型适用于地下水电导率的模拟预测。表4中所有监测井在训练和测试阶段的$ {{R}}^{2} $均大于0.98,RMSE均小于0.009,说明该模型在进行电导率的模拟预测时也表现出良好的性能。
在对比不同输入参数对地下水位预测结果的影响时,在模型训练完成后,关闭WA-NARX网络的回路,输出反馈进行多步预测。以60 h为时间步长进行多步预测。表5为仅有降雨、潮汐参数的地下水位预测结果与新增蒸发参数后(降雨、潮汐和蒸发)的地下水位预测结果的对比。由预测误差可知,输入参数仅为降雨和潮汐时,模型的预测精度较高;当在此基础上新增蒸发作为输入参数时,模型预测结果发生了变化。与无新增参数的结果相比,监测井BH1、BH3和BH6的预测精度有所提高,其余监测井的预测精度有所降低。经过整体对比发现,只有降雨和潮汐作为模型的输入参数时,模型的预测效果略高于新增蒸发参数后的预测效果。说明在该地区进行地下水位预测时,降雨和潮汐对地下水位变化的影响更为显著。
图11是新增蒸发参数后得到的预测水位与实测水位的散点图。图中实线是观测水位数据的连线,把降雨和潮汐作为WA-NARX模型的输入参数,预测60 h时间步长的地下水位时,模型的预测值基本分布在实测的水位线上,预测效果良好。新增蒸发参数后,监测井BH1、BH3和BH6的预测散点值更集中于实测水位线,表现出更好的预测效果,而其余观测井的预测效果相比之前有所下降,这与表5的分析结果一致。
农业排灌用电量与农业抽水灌溉有关,灌溉则与地下水位密切相关,所以把排灌用电量作为一组参数,研究其对地下水位预测的影响。表6为新增排灌用电量参数与只有降雨和潮汐作为参数时地下水位预测结果的对比。由预测误差可知,只有降雨和潮汐作为输入参数时模型有较高的预测精度;当新增排灌用电量作为输入参数后,模型的预测精度同之前相差甚小。其中监测井BH5、BH6的预测效果有细微的提高,其余监测井的预测效果有所降低。说明在研究区内农业排灌用电量数据可以作为预测地下水位的一项参数,在使用时要结合研究区监测井的实际情况,在农业抽水灌溉量较大处的影响会更显著。同时从电量时间序列可以看出,因统计关系,每个月的灌溉用电量基本为定值,而地下水位的预测周期是小时变化,所以,用电量的观测与地下水预测频率不完全一致,对模拟结果也有较大影响。如果用电量的统计频率与预测相符,模型的预测精度应有所提高。
图12是新增排灌用电量参数得到的预测水位与实测水位的散点图。从图中可以看出,每口井对新增排灌用电量参数后的预测效果响应并不尽相同。BH1与BH6的预测结果相对近似;而BH2、BH3及BH4的预测水位分布及表6中RMSE共同显示其预测值较只应用降水与潮汐时有所下降。对于BH5来说,加入用电量后预测结果整体向上偏移,精度有一定提高。对比结果说明井位地理位置分布及其区域地质条件对用电量的响应有较大关联。
图13是新增蒸发参数后得到的预测电导率与观测电导率的曲线图,表7为不同输入参数地下水电导率预测结果的对比统计表。由分析结果可知,在降雨、潮汐基础上增加蒸发数据作为输入参数时,无论在变化平缓区还是剧烈区,监测井中电导率的预测精度都有显著提高。特别对监测井BH5,未加入蒸发数据时预测值略有偏高,加入蒸发对该井有明显的校正作用。预测结果说明在该地区预测地下水电导率时,蒸发是重要影响因素。
为了对比不同输入参数对地下水电导率预测结果的影响,关闭WA-NARX网络的回路,输出反馈进行多步预测。把收集到的农业抽水排灌用电量数据作为一项参数,对比其对地下水电导率预测效果的影响。由表7可知,只有降雨和潮汐作为输入参数时,模型有较好预测效果;新增农业排灌用电量参数,监测井BH1、BH2和BH5的预测效果有所提高,其余监测井的预测效果基本保持一致,总体上新增排灌用电量参数后混合模型的预测效果有所提升。
图14是新增排灌用电量参数得到的预测电导率与观测电导率的曲线图。预测值的变化趋势和实测电导率的变化趋势基本吻合,表现出较好的预测效果;当新增农业排灌用电量参数时,监测井BH1、BH2和BH5的预测曲线与观测电导率曲线的变化趋势更加贴合,与表7的分析结果一致。
莱州湾南岸是受海水入侵影响严重地区。通过对沿海典型剖面含水层地下水位和电导率的变化分析可知,该区海水入侵季节性变化趋势明显。主要表现在地下水电导率与水位存在一定的负相关关系,在降雨补给充足的情况下,地下水水位有较为明显的上升趋势,地下水电导率降低,海水入侵程度减弱。但由于受地下水开采的影响,水位和电导率均存在突变现象,水位降低打破原有的咸淡水平衡,使海水入侵加剧。同时,本文建立了基于小波分析的非线性自回归神经网络混合模型(WA-NARX),分别对地下水位和地下水中的电导率进行预测,通过增加模型的输入参数,对比分析不同输入参数对模型预测效果的影响。研究发现,地下水位和电导率的变化与降雨和潮汐的变化密切相关。当降雨和潮汐作为模型的输入参数预测地下水位与电导率时,模型预测效果良好。蒸发参数和农业排灌用电量对地下水位与电导率也有一定影响。模型预测依然具有较高精度,个别观测点精度有所提高。通过上述研究表明,WA-NARX模型可以作为海水入侵预测的有效工具,不仅可以为水资源的高效利用提供参考,还可以掌握海岸带地下水盐度的变化,为海水入侵的监测预测预警、保护地下淡水资源及海岸带环境保护提供科学依据。
  • 山东省重大科技创新工程专项(2018SDKJ0503-2)
  • 国家自然科学基金面上项目(41702244)
  • 国家自然科学基金青年项目(41972249,41706067)
参考文献 引证文献
排序方式:
1
吴吉春, 吴永祥, 林锦, 等. 黄渤海沿海地区地下水管理与海水入侵防治研究[J]. 中国环境管理, 2018, 10(2): 91−92.
Wu Jichun, Wu Yongxiang, Lin Jin, et al. Study on the groundwater management and seawater intrusion prevention in the coastal areas of the Bohai Sea and the Yellow Sea[J]. Chinese Journal of Environmental Management, 2018, 10(2): 91−92.
2
高茂生, 骆永明. 我国重点海岸带地下水资源问题与海水入侵防控[J]. 中国科学院院刊, 2016, 31(10): 1197−1203.
Gao Maosheng, Luo Yongming. Change of groundwater resource and prevention and control of seawater intrusion in coastal zone[J]. Bulletin of Chinese Academy of Sciences, 2016, 31(10): 1197−1203.
3
Zhang Xiaoying, Qi Linlin, Li Wenming, et al. Bacterial community variations with salinity in the saltwater-intruded estuarine aquifer[J]. Science of the Total Environment, 2021, 755: 142423.
4
Zhang Xiaoying, Hu B X, Wang Peng, et al. Hydrogeochemical evolution and heavy metal contamination in groundwater of a reclaimed land on Zhoushan Island[J]. Water, 2018, 10(3): 316: 1−22.
5
孙娜, 周建中, 朱双, 等. 基于小波分析的两种神经网络耦合模型在月径流预测中的应用[J]. 水电能源科学, 2018, 36(4): 14−17, 32.
Sun Na, Zhou Jianzhong, Zhu Shuang, et al. Application of hybrid models based on wavelet analysis and two different neural networks in prediction of monthly runoff[J]. Water Resources and Power, 2018, 36(4): 14−17, 32.
6
Shoaib M, Shamseldin A Y, Melville B W, et al. A comparison between wavelet based static and dynamic neural network approaches for runoff prediction[J]. Journal of Hydrology, 2016, 535: 211−225.
7
Guzman S M, Paz J O, Tagert M L M. The use of NARX neural networks to forecast daily groundwater levels[J]. Water Resources Management, 2017, 31(5): 1591−1603.
8
Wunsch A, Liesch T, Broda S. Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX)[J]. Journal of Hydrology, 2018, 567: 743−758.
9
Di Nunno F, Granata F. Groundwater level prediction in Apulia region (Southern Italy) using NARX neural network[J]. Environmental Research, 2020, 190: 110062.
10
Cannas B, Fanni A, See L, et al. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning[J]. Physics and Chemistry of the Earth, Parts A/B/C, 2006, 31(18): 1164−1171.
11
Zhang Juan, Qiu Han, Li Xiaoyu, et al. Real-time nowcasting of microbiological water quality at recreational beaches: a wavelet and artificial neural network-based hybrid modeling approach[J]. Environmental Science & Technology, 2018, 52(15): 8446−8455.
12
Nason G P, Von Sachs R. Wavelets in time-series analysis[J]. Philosophical Transactions of the Royal Society A: Mathematical, Physical, and Engineering Sciences, 1999, 357(1760): 2511−2526.
13
Moosavi V, Vafakhah M, Shirmohammadi B, et al. A Wavelet-ANFIS hybrid model for groundwater level forecasting for different prediction periods[J]. Water Resources Management, 2013, 27(5): 1301−1321.
14
Zhang Xiaoying, Dong Fan, Dai Heng, et al. Influence of lunar semidiurnal tides on groundwater dynamics in estuarine aquifers[J]. Hydrogeology Journal, 2020, 28(4): 1419−1429.
15
Kisi O, Shiri J. Precipitation forecasting using wavelet-genetic programming and wavelet-neuro-fuzzy conjunction models[J]. Water Resources Management, 2011, 25(13): 3135−3152.
16
Mohanty S, Jha M K, Raul S K, et al. Using artificial neural network approach for simultaneous forecasting of weekly groundwater levels at multiple sites[J]. Water Resources Management, 2015, 29(15): 5521−5532.
17
Nourani V, Alami M T, Vousoughi F D, et al. Wavelet-entropy data pre-processing approach for ANN-based groundwater level modeling[J]. Journal of Hydrology, 2015, 524: 255−269.
18
Adamowski J, Chan H F. A wavelet neural network conjunction model for groundwater level forecasting[J]. Journal of Hydrology, 2011, 407(1/4): 28−40.
19
Gorgij A D, Kisi O, Moghaddam A A. Groundwater budget forecasting, using hybrid wavelet-ANN-GP modelling: a case study of Azarshahr Plain, East Azerbaijan, Iran[J]. Hydrology Research, 2017, 48(2): 455−467.
20
张建锋, 刘见宝, 崔树军, 等. 小波–神经网络混合模型预测地下水水位[J]. 长江科学院院报, 2016, 33(8): 18−21.
Zhang Jianfeng, Liu Jianbao, Cui Shujun, et al. A wavelet-ANN hybrid model for groundwater level forecasting[J]. Journal of Yangtze River Scientific Research Institute, 2016, 33(8): 18−21.
21
Seo Y, Kim S, Kisi O, et al. Daily water level forecasting using wavelet decomposition and artificial intelligence techniques[J]. Journal of Hydrology, 2015, 520: 224−243.
22
Zhang Juan, Zhang Xiaoying, Niu Jie, et al. Prediction of groundwater level in seashore reclaimed land using wavelet and artificial neural network-based hybrid model[J]. Journal of Hydrology, 2019, 577: 123948.
23
陈广泉. 莱州湾地区海水入侵的影响机制及预警评价研究[D]. 上海: 华东师范大学, 2013.
Chen Guangquan. Mechanisms underlying of seawater intrusion and evaluation of early warning systems in the Laizhou Bay area[D]. Shanghai: East China Normal University, 2013.
24
Chen Guangquan, Xiong Guiyao, Lin Jin, et al. Elucidating the pollution sources and groundwater evolution in typical seawater intrusion areas using hydrochemical and environmental stable isotope technique: a case study for Shandong Province, China[J]. Lithosphere, 2021, 2021(S3): 4227303.
25
苗晋杰. 莱州湾南岸海(咸)水入侵动态监测及演化研究[D]. 北京: 中国地质大学(北京), 2014.
Miao Jinjie. Dynamic monitoring and evolution study of saline intrusion at south coast of LaiZhou Bay[D]. Beijing: China University of Geosciences (Beijing), 2014.
26
Zhang Xiaoying, Miao Jinjie, Hu B X, et al. Hydrogeochemical characterization and groundwater quality assessment in intruded coastal brine aquifers (Laizhou Bay, China)[J]. Environmental Science and Pollution Research, 2017, 24(26): 21073−21090.
27
Gedalof Z, Smith D J. Interdecadal climate variability and regime-scale shifts in Pacific North America[J]. Geophysical Research Letters, 2001, 28(8): 1515−1518.
28
Grinsted A, Moore J C, Jevrejeva S. Application of the cross wavelet transform and wavelet coherence to geophysical time series[J]. Nonlinear Processes in Geophysics, 2004, 11(5/6): 561−566.
29
Mallat S G. A theory for multiresolution signal decomposition: the wavelet representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674−693.
30
Shensa M J. The discrete wavelet transform: wedding the a trous and Mallat algorithms[J]. IEEE Transactions on Signal Processing, 1992, 40(10): 2464−2482.
31
Elman J L. Finding structure in time[J]. Cognitive Science, 1990, 14(2): 179−211.
32
Lin T, Horne B G, Tino P, et al. Learning long-term dependencies in NARX recurrent neural networks[J]. IEEE Transactions on Neural Networks, 1996, 7(6): 1329−1338.
33
Chatterjee S, Nigam S, Singh J B, et al. Software fault prediction using Nonlinear Autoregressive with eXogenous Inputs (NARX) network[J]. Applied Intelligence, 2012, 37(1): 121−129.
34
柴琳娜, 屈永华, 张立新, 等. 基于自回归神经网络的时间序列叶面积指数估算[J]. 地球科学进展, 2009, 24(7): 756−768.
Chai Linna, Qu Yonghua, Zhang Lixin, et al. Estimating time series leaf area index based on recurrent neural networks[J]. Advances in Earth Science, 2009, 24(7): 756−768.
35
Adamowski J, Sun K R. Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds[J]. Journal of Hydrology, 2010, 390(1/2): 85−91.
36
Tiwari M K, Chatterjee C. Development of an accurate and reliable hourly flood forecasting model using wavelet-bootstrap-ANN (WBANN) hybrid approach[J]. Journal of Hydrology, 2010, 394(3/4): 458−470.
37
苗青. 降雨与潮汐作用对莱州湾地区海水入侵的影响机制研究[D]. 青岛: 国家海洋局第一海洋研究所, 2013.
Miao Qing. Effects of precipitation and tide on seawater intrusion in the Laizhou Bay[D]. Qingdao: The First Institute of Oceanography, State Oceanic Administration, 2013.
38
李志威, 张晓影, 张明珠, 等. 海水入侵指标对比分析与评价——以珠江口地下水含水层为例[J]. 海洋环境科学, 2020, 39(1): 16−24.
Li Zhiwei, Zhang Xiaoying, Zhang Mingzhu, et al. Comparison of indicators for the assessment of saltwater intrusion in coastal aquifers—taking aquifers in Pearl River Estuary as an example[J]. Marine Environmental Science, 2020, 39(1): 16−24.
39
王玉广, 王传珺, 刘志华, 等. 地下水位和海平面变化对绥中砂质海岸海水入侵影响[J]. 海洋环境科学, 2019, 38(3): 347−352.
Wang Yuguang, Wang Chuanjun, Liu Zhihua, et al. Impact to the the seawater intrusion around sand coast in Suizhong with the variations of groundwater level and sea level[J]. Marine Environmental Science, 2019, 38(3): 347−352.
40
覃光雄, 胡晓农, 张晓影, 等. 珠江河口区地下水盐分空间变异特征分析[J]. 海洋环境科学, 2018, 37(6): 835−842.
Qin Guangxiong, Hu Xiaonong, Zhang Xiaoying, et al. Characterization of groundwater salinity spatial variation in the Pearl River estuary[J]. Marine Environmental Science, 2018, 37(6): 835−842.
41
刘启和. 辽阳市地下水电导率特性研究[J]. 水利技术监督, 2017, 25(3): 60−62, 91.
Liu Qihe. Study on conductivity characteristics of groundwater in Liaoyang City[J]. Technical Supervision in Water Resources, 2017, 25(3): 60−62, 91.
42
章斌, 宋献方, 韩冬梅, 等. 运用数理统计和模糊数学评价秦皇岛洋戴河平原的海水入侵程度[J]. 地理科学, 2013, 33(3): 342−348.
Zhang Bin, Song Xianfang, Han Dongmei, et al. Seawater intrusion degree evaluation based on mathematical statistics and fuzzy mathematics in Qinhuangdao Yangdai River plain[J]. Scientia Geographica Sinica, 2013, 33(3): 342−348.
43
赵世彬, 陈广泉, 张晓影, 等. 潮汐影响下的海岸带地下河口水交换及其生物地球化学效应[J]. 海洋地质前沿, 2018, 34(9): 73−78.
Zhao Shibin, Chen Guangquan, Zhang Xiaoying, et al. Water exchange and biogeochemical effects of subterranean estuary with tide[J]. Marine Geology Frontiers, 2018, 34(9): 73−78.
2022年第44卷第3期
PDF下载
177
74
引用本文
BibTeX
文章信息
doi: 10.12284/hyxb2022015
  • 接收时间:2021-02-08
  • 首发时间:2026-02-01
  • 出版时间:2022-03-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2021-02-08
  • 修回日期:2021-10-06
基金
山东省重大科技创新工程专项(2018SDKJ0503-2)
国家自然科学基金面上项目(41702244)
国家自然科学基金青年项目(41972249,41706067)
作者信息
    1.吉林大学 建设工程学院,吉林 长春 130026
    2.自然资源部第一海洋研究所 自然资源部海岸带科学与综合管理重点实验室,山东 青岛 266061
    3.青岛海洋科学与技术试点国家实验室 海洋地质过程与环境功能实验室,山东 青岛 266237

通讯作者:

张晓影,女,副教授,博士生导师,主要从事非均质介质中溶质反应迁移模拟及尺度效应研究。E-mail:
陈广泉,男,高级工程师,主要从事海洋地质与海水入侵研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/hyxb/CN/10.12284/hyxb2022015
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