Article(id=1153420097063477909, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1153001424821674657, articleNumber=1671-1807(2025)08-0060-04, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1724169600000, receivedDateStr=2024-08-21, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1752926380648, onlineDateStr=2025-07-19, pubDate=1745510400000, pubDateStr=2025-04-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752926380648, onlineIssueDateStr=2025-07-19, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752926380648, creator=13701087609, updateTime=1752926380648, updator=13701087609, issue=Issue{id=1153001424821674657, tenantId=1146029695717560320, journalId=1146123222451335185, year='2025', volume='25', issue='8', pageStart='1', pageEnd='368', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752826561408, creator=13701087609, updateTime=1763438371676, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1197510583135286126, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1153001424821674657, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1197510583135286127, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1153001424821674657, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=60, endPage=63, ext={EN=ArticleExt(id=1153420097461936803, articleId=1153420097063477909, tenantId=1146029695717560320, journalId=1146123222451335185, language=EN, title=Application of Bayesian Model Averaging in the Simulation of Seafloor Water Temperatures in the Gulf of Maine, columnId=1151876674645226399, journalTitle=Science Technology and Industry, columnName=Technology Innovation, runingTitle=null, highlight=null, articleAbstract=

Coastal ocean circulation models have improved dramatically in recent decades, but it is still difficult to obtain sufficient data to constrain and validate simulations. National Oceanic and Atmospheric Administration, hereinafter referred to as NOAA, in cooperation with local fishing vessels, provides a low-cost data observing system that has produced a large number of hourly bottom temperature datasets over a wide area of the US Northeast Continental Shelf over a wide area, generating a large number of hourly bottom temperature datasets. In order to provide a better validation of the coastal ocean circulation model and to help fishermen have a better understanding of the fishing conditions, three existing ocean models were combined and the hourly real-time bottom temperature data was used as a reference to visualize the data from each ocean model and the data from multiple ocean models after Bayesian model averaging, which revealed that the performance of the Bayesian combined model was better. The Bayesian combination model is found to perform better.

, correspAuthors=Shuai YANG, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Mingchao GAO, Shuai YANG, Ning ZHANG, Yongming ZHANG), CN=ArticleExt(id=1153420114209792066, articleId=1153420097063477909, tenantId=1146029695717560320, journalId=1146123222451335185, language=CN, title=贝叶斯模型平均法在海底水温模拟中的应用, columnId=1151876674787832737, journalTitle=科技和产业, columnName=科技创新, runingTitle=null, highlight=null, articleAbstract=

近几十年来沿海海洋环流模型已得到显著改善,但仍然难以获得足够的数据来约束和验证模拟。北美海洋与大气管理局(National Oceanic and Atmospheric Administration, NOAA)与当地渔船合作提供了一个低成本的数据观测系统,该系统已在美国东北部海洋大陆架(the US northeast continental shelf)的广泛范围内产生大量的每小时底部温度数据集。为了给予沿海海洋环流模型更好地验证模拟以及帮助渔民更清楚地了解捕鱼状况,结合现有的三种海洋模型,以每小时实时海洋底部温度数据作为参照,将各个海洋模型的数据同多种海洋模型经过贝叶斯模型平均法处理之后的数据进行可视化产品评估分析,以此发现贝叶斯组合模型表现更佳。

, correspAuthors=杨帅, authorNote=null, correspAuthorsNote=
杨帅(1994—),男,山东临沂人,硕士,工程师,研究方向为地理信息系统开发
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=qDCLG+YaAuaUJHxK2dp/4w==, magXml=BHan/vwlixbl5pc2GCPF1A==, pdfUrl=null, pdf=E/e0Pu1YRaa2/d+uJ2gsBQ==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ltxlFwVfdXczepd0S7+mfQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ImfY3JS0i3ojGc5wIF08Fw==, mapNumber=null, authorCompany=null, fund=null, authors=

高明超(1996—),男,山东青岛人,硕士,工程师,研究方向为地理信息系统应用;

张宁(1996—)男,山东济南人,硕士,工程师,研究方向为集成数据分析处理;

张永明(1995—),男,山东济宁人,硕士,工程师,研究方向为数据可视化。

, authorsList=高明超, 杨帅, 张宁, 张永明)}, authors=[Author(id=1197613098086478628, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, orderNo=0, 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=1197613098161976102, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098086478628, language=EN, stringName=Mingchao GAO, firstName=Mingchao, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1197613098241667879, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098086478628, language=CN, stringName=高明超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=济南市勘察测绘研究院, 济南 250101, bio={"content":"

高明超(1996—),男,山东青岛人,硕士,工程师,研究方向为地理信息系统应用;

"}, bioImg=null, bioContent=

高明超(1996—),男,山东青岛人,硕士,工程师,研究方向为地理信息系统应用;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1197613098002592543, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, xref=null, ext=[AuthorCompanyExt(id=1197613098010981152, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China), AuthorCompanyExt(id=1197613098019369761, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=济南市勘察测绘研究院, 济南 250101)])]), Author(id=1197613098308776746, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1197613098380079917, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098308776746, language=EN, stringName=Shuai YANG, firstName=Shuai, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1197613098480743214, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098308776746, language=CN, stringName=杨帅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=济南市勘察测绘研究院, 济南 250101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1197613098002592543, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, xref=null, ext=[AuthorCompanyExt(id=1197613098010981152, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China), AuthorCompanyExt(id=1197613098019369761, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=济南市勘察测绘研究院, 济南 250101)])]), Author(id=1197613098568823600, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1197613098635932466, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098568823600, language=EN, stringName=Ning ZHANG, firstName=Ning, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1197613098698847027, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098568823600, language=CN, stringName=张宁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=济南市勘察测绘研究院, 济南 250101, bio={"content":"

张宁(1996—)男,山东济南人,硕士,工程师,研究方向为集成数据分析处理;

"}, bioImg=null, bioContent=

张宁(1996—)男,山东济南人,硕士,工程师,研究方向为集成数据分析处理;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1197613098002592543, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, xref=null, ext=[AuthorCompanyExt(id=1197613098010981152, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China), AuthorCompanyExt(id=1197613098019369761, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=济南市勘察测绘研究院, 济南 250101)])]), Author(id=1197613098753372982, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, 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=1197613098870813499, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098753372982, language=EN, stringName=Yongming ZHANG, firstName=Yongming, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1197613098925339453, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, authorId=1197613098753372982, language=CN, stringName=张永明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=济南市勘察测绘研究院, 济南 250101, bio={"content":"

张永明(1995—),男,山东济宁人,硕士,工程师,研究方向为数据可视化。

"}, bioImg=null, bioContent=

张永明(1995—),男,山东济宁人,硕士,工程师,研究方向为数据可视化。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1197613098002592543, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, xref=null, ext=[AuthorCompanyExt(id=1197613098010981152, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China), AuthorCompanyExt(id=1197613098019369761, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=济南市勘察测绘研究院, 济南 250101)])])], keywords=[Keyword(id=1197613100061995839, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, orderNo=1, keyword=ocean modeling), Keyword(id=1197613100133299009, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, orderNo=2, keyword=Bayesian model averaging), Keyword(id=1197613100208796482, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, orderNo=3, keyword=ocean bottom temperature data), Keyword(id=1197613100305265476, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, orderNo=1, keyword=海洋模型), Keyword(id=1197613100431094597, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, orderNo=2, keyword=贝叶斯模型平均法), Keyword(id=1197613100510786376, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, orderNo=3, keyword=海洋底部温度数据)], refs=[Reference(id=1197613101962015588, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=5152, pageEnd=5161, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=尤立, 齐天杰, 胡春明, journalName=科学技术与工程, refType=null, unstructuredReference=尤立, 齐天杰, 胡春明. 斯里兰卡极端降水时空演变特征及趋势预测[J]. 科学技术与工程, 2024, 24(12): 5152-5161., articleTitle=斯里兰卡极端降水时空演变特征及趋势预测, refAbstract=null), Reference(id=1197613102050095973, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=3, pageStart=19, pageEnd=23, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=王亮, journalName=技术经济与管理研究, refType=null, unstructuredReference=王亮. 贝叶斯模型平均方法研究综述与展望[J]. 技术经济与管理研究, 2016(3): 19-23., articleTitle=贝叶斯模型平均方法研究综述与展望, refAbstract=null), Reference(id=1197613102180119399, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2017, volume=9, issue=2, pageStart=74, pageEnd=90, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=QU B, ZHANG X, PAPPENBERGER F, journalName=Water, refType=null, unstructuredReference=QU B, ZHANG X, PAPPENBERGER F, et al. Multi-model grand ensemble hydrologic forecasting in the Fu River Basin using Bayesian model averaging[J]. Water, 2017, 9(2): 74-90., articleTitle=Multi-model grand ensemble hydrologic forecasting in the Fu River Basin using Bayesian model averaging, refAbstract=null), Reference(id=1197613102234645352, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=刘晓建, journalName=芬迪湾环流中亚历山大藻颗粒轨迹的模拟研究, refType=null, unstructuredReference=刘晓建. 芬迪湾环流中亚历山大藻颗粒轨迹的模拟研究[D]. 青岛: 山东科技大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1197613102305948521, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=7, pageStart=172, pageEnd=178, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=张芷若, 肖喜萌, journalName=科技和产业, refType=null, unstructuredReference=张芷若, 肖喜萌. 黄河流域经济高质量发展与生态环境耦合协调的时空演化[J]. 科技和产业, 2024, 24(7): 172-178., articleTitle=黄河流域经济高质量发展与生态环境耦合协调的时空演化, refAbstract=null), Reference(id=1197613102398223211, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=3, pageStart=13, pageEnd=20, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=刘恒, journalName=水力发电, refType=null, unstructuredReference=刘恒. 基于贝叶斯平均法的洪水分类组合预报研究[J]. 水力发电, 2020, 46(3): 13-20., articleTitle=基于贝叶斯平均法的洪水分类组合预报研究, refAbstract=null), Reference(id=1197613102503080813, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=4, pageStart=192, pageEnd=198, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=潘成蓉, 雷敏, journalName=科技和产业, refType=null, unstructuredReference=潘成蓉, 雷敏. 光伏发电企业运营效率及影响因素研究——基于DEA-Malmquist-Tobit模型的分析[J]. 科技和产业, 2024, 24(4): 192-198., articleTitle=光伏发电企业运营效率及影响因素研究——基于DEA-Malmquist-Tobit模型的分析, refAbstract=null), Reference(id=1197613102649881456, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=赵亦君, journalName=基于贝叶斯网络的器质性精神障碍筛查模型研究, refType=null, unstructuredReference=赵亦君. 基于贝叶斯网络的器质性精神障碍筛查模型研究[D]. 济南: 山东大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1197613102725378930, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=史伟克, journalName=基于FVCOM初始场的可预报性研究, refType=null, unstructuredReference=史伟克. 基于FVCOM初始场的可预报性研究[D]. 哈尔滨: 哈尔滨工程大学, 2024., articleTitle=null, refAbstract=null), Reference(id=1197613102817653620, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=18, pageStart=7928, pageEnd=7939, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=蒋松谕, 何贞铭, 周再文, journalName=科学技术与工程, refType=null, unstructuredReference=蒋松谕, 何贞铭, 周再文, 等. 二次分解策略的深度学习碳交易价格预测[J]. 科学技术与工程, 2024, 24(18): 7928-7939., articleTitle=二次分解策略的深度学习碳交易价格预测, refAbstract=null), Reference(id=1197613102880568182, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=3, pageStart=210, pageEnd=215, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=肖田田, journalName=科技和产业, refType=null, unstructuredReference=肖田田. 基于K-means-LSTM模型的证券股价预测[J]. 科技和产业, 2024, 24(3): 210-215., articleTitle=基于K-means-LSTM模型的证券股价预测, refAbstract=null), Reference(id=1197613102951871352, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=王艺天, journalName=基于深度学习的地铁短时客流预测研究, refType=null, unstructuredReference=王艺天. 基于深度学习的地铁短时客流预测研究[D]. 大连: 大连交通大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1197613103010591609, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=5, pageStart=26, pageEnd=31, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=喻婷, 龚绍琦, 严清赟, journalName=海洋测绘, refType=null, unstructuredReference=喻婷, 龚绍琦, 严清赟, 等. CYGNSS卫星风速产品的精度检验[J]. 海洋测绘, 2021, 41(5): 26-31., articleTitle=CYGNSS卫星风速产品的精度检验, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1197613098002592543, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, xref=null, ext=[AuthorCompanyExt(id=1197613098010981152, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China), AuthorCompanyExt(id=1197613098019369761, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, companyId=1197613098002592543, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=济南市勘察测绘研究院, 济南 250101)])], figs=[ArticleFig(id=1197613100787610442, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, label=null, caption=null, figureFileSmall=3ZpqvZUm75CUoy1MNH8+hw==, figureFileBig=7+Pp8aKRN1yumWqRT/P2qA==, tableContent=null), ArticleFig(id=1197613100884079437, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, label=图1, caption=两种不同模型的后验概率对比, figureFileSmall=3ZpqvZUm75CUoy1MNH8+hw==, figureFileBig=7+Pp8aKRN1yumWqRT/P2qA==, tableContent=null), ArticleFig(id=1197613101005714255, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, label=null, caption=null, figureFileSmall=5vqvQd2wtadiDfs0pcCVhQ==, figureFileBig=xptEVq5F749h8sdXRT+UeQ==, tableContent=null), ArticleFig(id=1197613101056045905, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, label=图2, caption=BMA组合模型构建流程, figureFileSmall=5vqvQd2wtadiDfs0pcCVhQ==, figureFileBig=xptEVq5F749h8sdXRT+UeQ==, tableContent=null), ArticleFig(id=1197613101127349075, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, label=null, caption=null, figureFileSmall=lIClP6oZN/+CFJO8pJnwmw==, figureFileBig=y/n1fY0vM79w+3Iub6k4kg==, tableContent=null), ArticleFig(id=1197613101211235157, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, label=图3, caption=各模型同观测值差值对比, figureFileSmall=lIClP6oZN/+CFJO8pJnwmw==, figureFileBig=y/n1fY0vM79w+3Iub6k4kg==, tableContent=null), ArticleFig(id=1197613101274149719, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, label=null, caption=null, figureFileSmall=ldZvmX2FBG3sEX86W0V+Xg==, figureFileBig=v7LgPv9f/hNdMKAB7wAcVQ==, tableContent=null), ArticleFig(id=1197613101362230105, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, label=图4, caption=各模型的泰勒图对比, figureFileSmall=ldZvmX2FBG3sEX86W0V+Xg==, figureFileBig=v7LgPv9f/hNdMKAB7wAcVQ==, tableContent=null), ArticleFig(id=1197613101525807963, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
时间 Lat/(°) Lon/(°) 海底温度/℃
2019-01-02 15:17 42.XX 70.XX 7.52
2020-03-031 19:24 40.XX 70.XX 8.4
), ArticleFig(id=1197613101592916829, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, label=表1, caption=

海底温度采集数据

, figureFileSmall=null, figureFileBig=null, tableContent=
时间 Lat/(°) Lon/(°) 海底温度/℃
2019-01-02 15:17 42.XX 70.XX 7.52
2020-03-031 19:24 40.XX 70.XX 8.4
), ArticleFig(id=1197613101655831391, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
时间 观测值/℃ DOPPIO/℃ FVCOM/℃ GOMOFS/℃ BMA/℃
2019-01-02 18:22:00 7.34 7.95 8.58 8.56 8.19
2019-09-010 11:31:00 13.27 11.59 15.59 13.84 13.06
2020-03-031 19:24:00 8.40 8.38 6.59 9.00 7.75
), ArticleFig(id=1197613101769077601, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153420097063477909, language=CN, label=表2, caption=

BMA组合模型预测值

, figureFileSmall=null, figureFileBig=null, tableContent=
时间 观测值/℃ DOPPIO/℃ FVCOM/℃ GOMOFS/℃ BMA/℃
2019-01-02 18:22:00 7.34 7.95 8.58 8.56 8.19
2019-09-010 11:31:00 13.27 11.59 15.59 13.84 13.06
2020-03-031 19:24:00 8.40 8.38 6.59 9.00 7.75
)], attaches=null, journal=Journal(id=1146119232468656133, delFlag=0, nameCn=科技和产业, nameEn=Science Technology and Industry, nameHistory1=null, nameHistory2=null, issn=1671-1807, eissn=, cn=11-4671/T, coden=null, periodic=3, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=65omA9nasEwsJtKyya4q2A==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Ind, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755589264235, createdBy=null, updatedBy=15831073675, firstLetterCn=S, firstLetterEn=S, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=65omA9nasEwsJtKyya4q2A==, picEn=/wwFtLNQXxKpecNSjAf1AQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1164589040427811221, language=CN, name=科技和产业, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.kjhcy.org/kjycy/home, createdTime=1755589264256, updatedTime=1755589264256, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=http://www.kjhcy.org/kjycy/site/menu/20110121105642001, submissionAuthorUrl=http://www.kjhcy.org/kjycy/author/login, submissionEditorUrl=http://www.kjhcy.org/kjycy/editor/login, submissionReviewUrl=http://www.kjhcy.org/kjycy/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1164589040473948566, language=EN, name=Science Technology and Industry, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.kjhcy.org/kjycy/home, createdTime=1755589264267, updatedTime=1755589264267, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.kjhcy.org/kjycy/author/login, submissionEditorUrl=http://www.kjhcy.org/kjycy/editor/login, submissionReviewUrl=http://www.kjhcy.org/kjycy/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123222451335185, websiteList=[Website(id=1148243202395595182, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123222451335185, 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/kjhcy/CN, language=CN, createTime=1751692112778, createBy=18614031015, updateTime=1753522130587, updateBy=18614031015, name=科技和产业-中文站点, tplId=1146099689490845704, title=科技和产业, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155919343281103033, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=articleTextType, value=kx, createTime=1753522247381, updateTime=1753522247381, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343260131510, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=banner, value=null, createTime=1753522247376, updateTime=1753522247376, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343251742901, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=NeDGaoVSnAwTO5bjjrifjg==, createTime=1753522247374, updateTime=1753522247374, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343272714424, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753522247379, updateTime=1753522247379, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343268520119, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753522247378, updateTime=1753522247378, creator=18614031015, updator=18614031015)]), Website(id=1155919131955314719, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123222451335185, 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/kjhcy/EN, language=EN, createTime=1753522197002, createBy=18614031015, updateTime=1753522207756, updateBy=18614031015, name=科技和产业-英文站点, tplId=1146101810881728533, title=Science Technology and Industry, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155919498877194448, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=articleTextType, value=kx, createTime=1753522284478, updateTime=1753522284478, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498860417229, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=banner, value=null, createTime=1753522284474, updateTime=1753522284474, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498852028620, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=NeDGaoVSnAwTO5bjjrifjg==, createTime=1753522284472, updateTime=1753522284472, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498873000143, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753522284477, updateTime=1753522284477, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498864611534, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753522284476, updateTime=1753522284476, creator=18614031015, updator=18614031015)])], journalTitle=科技和产业, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Industry, journalPhotoCn=65omA9nasEwsJtKyya4q2A==, journalPhotoEn=/wwFtLNQXxKpecNSjAf1AQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kjhcy/CN/Y2025/V25/I8/60, detailUrlEn=https://castjournals.cast.org.cn/joweb/kjhcy/EN/Y2025/V25/I8/60, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kjhcy/CN/PDF/Y2025/V25/I8/60, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kjhcy/EN/PDF/Y2025/V25/I8/60, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
贝叶斯模型平均法在海底水温模拟中的应用
收藏切换
PDF下载
高明超 , 杨帅 , 张宁 , 张永明
科技和产业 | 科技创新 2025,25(8): 60-63
收起
收藏切换
科技和产业 | 科技创新 2025, 25(8): 60-63
贝叶斯模型平均法在海底水温模拟中的应用
全屏
高明超, 杨帅, 张宁, 张永明
作者信息
  • 济南市勘察测绘研究院, 济南 250101
  • 高明超(1996—),男,山东青岛人,硕士,工程师,研究方向为地理信息系统应用;

    张宁(1996—)男,山东济南人,硕士,工程师,研究方向为集成数据分析处理;

    张永明(1995—),男,山东济宁人,硕士,工程师,研究方向为数据可视化。

通讯作者:

杨帅(1994—),男,山东临沂人,硕士,工程师,研究方向为地理信息系统开发
Application of Bayesian Model Averaging in the Simulation of Seafloor Water Temperatures in the Gulf of Maine
Mingchao GAO, Shuai YANG, Ning ZHANG, Yongming ZHANG
Affiliations
  • Jinan Geotechnical Investigation and Surveying Institute, Jinan 250101, China
出版时间: 2025-04-25
文章导航
收藏切换

近几十年来沿海海洋环流模型已得到显著改善,但仍然难以获得足够的数据来约束和验证模拟。北美海洋与大气管理局(National Oceanic and Atmospheric Administration, NOAA)与当地渔船合作提供了一个低成本的数据观测系统,该系统已在美国东北部海洋大陆架(the US northeast continental shelf)的广泛范围内产生大量的每小时底部温度数据集。为了给予沿海海洋环流模型更好地验证模拟以及帮助渔民更清楚地了解捕鱼状况,结合现有的三种海洋模型,以每小时实时海洋底部温度数据作为参照,将各个海洋模型的数据同多种海洋模型经过贝叶斯模型平均法处理之后的数据进行可视化产品评估分析,以此发现贝叶斯组合模型表现更佳。

海洋模型  /  贝叶斯模型平均法  /  海洋底部温度数据

Coastal ocean circulation models have improved dramatically in recent decades, but it is still difficult to obtain sufficient data to constrain and validate simulations. National Oceanic and Atmospheric Administration, hereinafter referred to as NOAA, in cooperation with local fishing vessels, provides a low-cost data observing system that has produced a large number of hourly bottom temperature datasets over a wide area of the US Northeast Continental Shelf over a wide area, generating a large number of hourly bottom temperature datasets. In order to provide a better validation of the coastal ocean circulation model and to help fishermen have a better understanding of the fishing conditions, three existing ocean models were combined and the hourly real-time bottom temperature data was used as a reference to visualize the data from each ocean model and the data from multiple ocean models after Bayesian model averaging, which revealed that the performance of the Bayesian combined model was better. The Bayesian combination model is found to perform better.

ocean modeling  /  Bayesian model averaging  /  ocean bottom temperature data
高明超, 杨帅, 张宁, 张永明. 贝叶斯模型平均法在海底水温模拟中的应用. 科技和产业, 2025 , 25 (8) : 60 -63 .
Mingchao GAO, Shuai YANG, Ning ZHANG, Yongming ZHANG. Application of Bayesian Model Averaging in the Simulation of Seafloor Water Temperatures in the Gulf of Maine[J]. Science Technology and Industry, 2025 , 25 (8) : 60 -63 .
借助海洋模型[1]参与海洋空间规划,人们能够更加清楚地了解沿海环境同海洋的特点及其联系。为了给予沿海海洋环流模型更好地验证模拟以及帮助渔民更清楚地了解捕鱼状况,本文结合现有的三种海洋模型,以每小时实时海洋底部温度数据作为参照,将各个海洋模型的数据同多种海洋模型经过贝叶斯模型平均法[2]处理之后的数据进行可视化产品评估分析,以此发现贝叶斯组合模型表现更佳[3]
通过美国综合海洋观测系统添加易于访问的海洋数据使得海洋数值模型者能够调整其设置、边界条件所需的信息以及量化不确定性,以此在近几十年来不断使用数据进行同化和验证来改进模型性能。虽然近几十年来沿海海洋环流模型有了很大的改进,但在获得足够的数据以约束和验证模拟方面仍然存在困难。鉴于海洋的广阔,特别是一些沿海环境和大陆架地形的复杂性,很难在足够的位置进行数据获取。尽管美国东北大陆架通过联邦补助报告系统(federal subaward reporting system,FSRS)安置了部分全自动的系泊监测设备,但它们在宽广的大陆架上设置和维护是非常昂贵的,而且它们提供的信息范围是有限[4-5]
为了改善这种情况,北美海洋与大气管理局与当地渔船合作提供一个低成本的数据观测系统—实时诱捕龙虾及环境监测船(environmental monitors on lobster traps and studyfleet realtime,eMOLT-StudyFleet realtime),该系统已在美国东北部海洋大陆架的广泛范围内产生大量的每小时底部温度数据集(表1)。该数据观测系统弥补了传统观测的劣势,其监测范围更广、数据更具有有效性,能够帮助模型建造者更好地同化数据、改善模型,此外更能够协助渔民获取到捕捞信息,大大提高捕捞效率[4-7]
贝叶斯模型平均方法(Bayesian model averaging, BMA)是在贝叶斯公式的基础之上,将模型本身的不确定性考虑在内的统计分析方法,其采用多种模型进行概率预测的统计处理,通过提高模拟结果来改善综合计算[2]
BMA方法是一种分析概率分布的工具,以多个模型的后验概率作为权系数来推导预测量。它不仅提供一个综合预测值,还能够得到一种不确定区间,为国内外研究学者提供一种针对模拟结果进行描述的参照准则。BMA组合预测避开了其他预测模型的缺点,包括未考虑主观先验信息、未充分利用每个预测方法准确的估计信息以及未考虑模型的不确定因素[2]。贝叶斯模型平均方法在后续模型筛选过程中,由于模型空间较大且需要对一组最优模型或者多组次优模型进行预测,通常采用模型后验概率作为挑选模型的标准,后验概率占比越高则对应的模型具备越好的预测效果。因为在最优化问题的解决上,通常是依据结构风险最小化或经验风险最小化对最优模型进行求解。在结构风险最小化的情况之下,模型的后验概率值与模型的优异性呈正相关,当后验概率达到最大值时,模型为最优模型。在随后的计算中,后验概率越大的模型,筛选阶段通过的概率越大[3-5]
BMA方法的实质就是以各个模型的后验概率作为权系数,通过对单一模型的预测值加权平均来获得贝叶斯模型平均值,其基本表述如下:
yBMA=$\sum _{i=1}^{m}$Pr(Mi|D)${y}_{{M}_{i}}$(t)
式中:yBMA为BMA方法的组合预测值;Pr(Mi|D)为给定数据D的情况下模型的后验概率;${y}_{{M}_{i}}$为单个模型Mi的预测值;t代表变量。
当实测数据D的大小增长到无穷大时,如果存在正确的模型,贝叶斯模型平均方法能保证正确的模型获得更高的后验概率Pr(Mi|D),在组合当中占有更高的比例。如图1所示。
沿海海洋环流模型自出现以来,广泛用于生态系统的评估以及渔业、水产养殖、航运和近海能源等以工业为基础的部门进行研究。美国东北部海洋大陆架范围内现有的三种主流海洋模型分别为ROMS-DOPPIO(regional ocean modeling system-a double experimental system for predicting shelf and slope optics,以下简称DOPPIO)、FVCOM-GoM3(the third generation of the unstructured grid finite volume community ocean model,以下简称FVCOM)和ROMS-GOMOFS(regional ocean modeling system: gulf of maine operational forecast system,以下简称GOMOFS),其中DOPPIO是2017年投入到海洋温度模拟预测当中,其之前为ESPResSo(extensible simulation package for research on soft matter)海洋模型;而FVCOM和GOMOFS海洋模型分别于1978年、2015年投入海洋温度模拟预测中,至今仍服务于缅因湾海底温度预测[7-8]
假设∀代表想要研究的预测变量、D代表实测数据、M=|M1,M2,…,Mn|代表n种模型组成的模型预测集合[9-11]。根据贝叶斯模型平均方法,∀的后验分布为
$Pr(\forall \left|D\right.)=\sum _{i=1}^{n}Pr(\forall |{M}_{i},D\left)Pr\right({M}_{i}\left|D\right.),i=\mathrm{1,2},\dots,n $
式中:Pr(∀|Mi,D)为给定模型Mi和实测数据D的条件下∀的后验分布;Pr(Mi|D)为给定实测数据D的条件下Mi是最优模型的概率。
结合式(2)可知,给定模型Mi的后验概率Pr(Mi|D)为
Pr(Mi|D)=Pr(D|Mi)Pr(Mi)
式中:Pr(Mi)为模型Mi是最优模型的先验概率,为了避免主观色彩对模型优劣的影响,通常指定相同的模型先验概率;Pri(D|Mi)为模型Mi的边际似然。
通过对未知参数进行积分,可求得模型Mi的边际似然Pri(D|Mi):
$P{r}_{i}\left(\left.D\right|{M}_{i}\right)=\int \dots \int P{r}_{i}\left(D\right|\beta,{M}_{i}\left)P{r}_{d}\right(\left.\beta \right|{M}_{i}){d}_{\beta }, \beta =(\beta 0,\beta 1,\dots,\beta n)$
式中:β为模型Mi的参数向量;Prd(β|Mi)为给定模型Mi的条件下β的先验信息,通常指定单位信息先验,如Raftery提出的多变量正态先验;Pri(D|β,Mi)为给定模型Mi与参数向量β的条件下实测数据D的似然[11-13]
结合式(2)~式(4),以各个模型的后验概率Pr(Mi|D)作为权系数值,对各个模型的预测值进行加权平均,可得BMA组合预测值为
yBMA=$\sum _{i=1}^{n}$Pr(Mi|D)${y}_{{M}_{i}}$(t)
式中:yBMA为BMA方法的组合预测值;Pr(Mi|D)为给定数据D的情况下模型的后验概率;${y}_{{M}_{i}}$为单个模型Mi的预测值;t为变量。
结合前人研究发现DOPPIO、FVCOM和GOMOFS三种海洋模型在不同区域和不同季节的预测情况各有所长[7]。鉴于此,本文以表2中的采集温度数据作为原始数据,通过DOPPIO、FVCOM和GOMOFS三种海洋温度模型进行海底温度模拟预测,获得模型预测初始数据,首先将模型预测初始数据中2019年1月—2020年3月(2019年11月采集数据不全,已剔除)这14个月的数据进行分类处理,其中每个月随机挑选10个数据作为预测部分,共计140条数据;随后将剩余的1 677条数据作为测试部分,以BMA组合模型算法设计作为理论基础(图2),最后结合Python进行后验概率加权计算(https://github.com/mamunm/BayesianFramework)以及可视化展示。
差值对比如图3所示,BMA组合模型的平均误差为0.014、RMS为1.2,在与另外三个模型的“与观测值温度误差对比”中,综合预测性能最好;其不但继承了DOPPIO模型的近海预测优势,在近海预测偏差颜色现实中,更趋近于0的颜色;此外在远海温度预测中,结合FVCOM与GOMOFS的远海预测优势,一定程度上补足DOPPIO远海温度预测短板。由图4可知,BMA组合模型的RMSD为1.185 7、SDEV为2.530 8、CC为0.928 0、BIAS为-0.014 4,均为四者中最优值。综合来看,BMA组合模型在海底温度预测中效果要优于其他三种海洋温度预测模型。
本文以海底水温作为研究对象,鉴于DOPPIO、FVCOM和GOMOFS三种单一海洋模型在数据预测方面存在一定的局限性,故引入贝叶斯模型平均方法,通过结合三种单一海洋模型的先验信息和先验概率求取各个模型的后验概率,以后验概率作为权重系数对三种海洋预测模型进行加权平均来构建BMA组合模型,并对海底水温进行可视化分析, 最终得出BMA组合模型的总体预测效果要优于其余三种单一模型。
参考文献 引证文献
排序方式:
[1]
尤立, 齐天杰, 胡春明. 斯里兰卡极端降水时空演变特征及趋势预测[J]. 科学技术与工程, 2024, 24(12): 5152-5161.
[2]
王亮. 贝叶斯模型平均方法研究综述与展望[J]. 技术经济与管理研究, 2016(3): 19-23.
[3]
QU B, ZHANG X, PAPPENBERGER F, et al. Multi-model grand ensemble hydrologic forecasting in the Fu River Basin using Bayesian model averaging[J]. Water, 2017, 9(2): 74-90.
[4]
刘晓建. 芬迪湾环流中亚历山大藻颗粒轨迹的模拟研究[D]. 青岛: 山东科技大学, 2020.
[5]
张芷若, 肖喜萌. 黄河流域经济高质量发展与生态环境耦合协调的时空演化[J]. 科技和产业, 2024, 24(7): 172-178.
[6]
刘恒. 基于贝叶斯平均法的洪水分类组合预报研究[J]. 水力发电, 2020, 46(3): 13-20.
[7]
潘成蓉, 雷敏. 光伏发电企业运营效率及影响因素研究——基于DEA-Malmquist-Tobit模型的分析[J]. 科技和产业, 2024, 24(4): 192-198.
[8]
赵亦君. 基于贝叶斯网络的器质性精神障碍筛查模型研究[D]. 济南: 山东大学, 2023.
[9]
史伟克. 基于FVCOM初始场的可预报性研究[D]. 哈尔滨: 哈尔滨工程大学, 2024.
[10]
蒋松谕, 何贞铭, 周再文, 等. 二次分解策略的深度学习碳交易价格预测[J]. 科学技术与工程, 2024, 24(18): 7928-7939.
[11]
肖田田. 基于K-means-LSTM模型的证券股价预测[J]. 科技和产业, 2024, 24(3): 210-215.
[12]
王艺天. 基于深度学习的地铁短时客流预测研究[D]. 大连: 大连交通大学, 2023.
[13]
喻婷, 龚绍琦, 严清赟, 等. CYGNSS卫星风速产品的精度检验[J]. 海洋测绘, 2021, 41(5): 26-31.
2025年第25卷第8期
PDF下载
313
161
引用本文
BibTeX
文章信息
  • 接收时间:2024-08-21
  • 首发时间:2025-07-19
  • 出版时间:2025-04-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-08-21
基金
作者信息
    济南市勘察测绘研究院, 济南 250101

通讯作者:

杨帅(1994—),男,山东临沂人,硕士,工程师,研究方向为地理信息系统开发
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kjhcy/CN/1153420097063477909
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