Article(id=1209819471896768602, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405116, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1720368000000, receivedDateStr=2024-07-08, revisedDate=1766419200000, revisedDateStr=2025-12-23, acceptedDate=null, acceptedDateStr=null, onlineDate=1766373039459, onlineDateStr=2025-12-22, pubDate=1751904000000, pubDateStr=2025-07-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1766373039459, onlineIssueDateStr=2025-12-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1766373039459, creator=13701087609, updateTime=1766373039459, updator=13701087609, issue=Issue{id=1209811339510411616, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='19', pageStart='7885', pageEnd='8315', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1766371100547, creator=13701087609, updateTime=1766373228996, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1209820266960654935, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1209820266960654936, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=8282, endPage=8288, ext={EN=ArticleExt(id=1209819472274255965, articleId=1209819471896768602, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Flight Delay Prediction Based on Informer Modeling, columnId=1209819472207147100, journalTitle=Science Technology and Engineering, columnName=Papers∙Aeronautics and Astronautics, runingTitle=null, highlight=null, articleAbstract=

In order to more accurately predict flight delays at different times of the year,flight delay prediction trends was investigated using operational and meteorological data from Atlanta Airport in the United States for the year 2023. A CA-PCA-Informer flight delay prediction model,incorporating correlation analysis (CA),principal component analysis (PCA),and the Informer model,was proposed. Mean absolute error (MAE) and root mean square error (RMSE) were utilized as evaluation metrics to assess the prediction error. The findings reveal that the CA-PCA-Informer model outperforms simpler combined models,demonstrating the lowest error compared to the CA-PCA-LSTM and CA-PCA-GRU models,with MAE and RMSE reductions of 20.2%~20.7% and 12.7%~14.1%,respectively. The CA-PCA-Informer model is particularly effective for one-hour ahead predictions,providing decision-makers with more accurate flight delay trends to enhance efficient flight operations.

, correspAuthors=null, 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=Xin-sheng YANG, Chao YOU, Cheng-yuan ZHU), CN=ArticleExt(id=1209819474300104822, articleId=1209819471896768602, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于Informer模型的航班延误预测, columnId=1209819472362336350, journalTitle=科学技术与工程, columnName=论文∙航空、航天, runingTitle=null, highlight=null, articleAbstract=为能更加精准预测不同时段的航班延误态势,选用美国亚特兰大机场2023年全年的运行数据与相关气象数据进行实验,提出基于相关系分析(correlation analysis,CA),主成分分析(principal components analysis,PCA)和Informer模型的CA-PCA-Informer航班延误预测模型,采用MAE(mean absolute error)和RMSE(root mean square error)作为模型的评价指标进行预测误差分析。结果表明,CA-PCA-Informer模型比简单的组合模型预测效果更好,与CA-PCA-LSTM和CA-PCA-GRU模型相比模型误差最低,MAE和RMSE分别降低了20.2%~20.7%和12.7%~14.1%;CA-PCA-Informer模型对预测步长为1 h时预测更为精准,该模型可以为决策者提供更加准确的航班延误态势以保证航班的高效运行。, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=HzpriBjHJ5hvWU5X2WnL7Q==, magXml=ATMcRH3pkgJM8L7mDzAtlw==, pdfUrl=null, pdf=fnpjrR0jp9gYbEaRdqkFDw==, pdfFileSize=5446295, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=KS0JSuM/xQdmNwRhZk68+w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=VFvv4Ffz5OYiW9Q6b46JzA==, mapNumber=null, authorCompany=null, fund=null, authors=

杨新湦( 1966—),男,汉族,陕西扶风人,硕士,教授。研究方向:交通运输规划与管理。E-mail:

, authorsList=杨新湦, 游超, 朱承元)}, authors=[Author(id=1209885640079053702, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=na785319178@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209885640167134088, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, authorId=1209885640079053702, language=EN, stringName=Xin-sheng YANG, firstName=Xin-sheng, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885640234242954, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, authorId=1209885640079053702, language=CN, stringName=杨新湦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国民航大学空中交通管理学院, 天津 300300, bio={"content":"

杨新湦( 1966—),男,汉族,陕西扶风人,硕士,教授。研究方向:交通运输规划与管理。E-mail:

"}, bioImg=null, bioContent=

杨新湦( 1966—),男,汉族,陕西扶风人,硕士,教授。研究方向:交通运输规划与管理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885639873532794, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, xref=1, ext=[AuthorCompanyExt(id=1209885639881921404, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639873532794, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1209885639886115709, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639873532794, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学空中交通管理学院, 天津 300300)])]), Author(id=1209885640301351822, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, 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=1209885640393626513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, authorId=1209885640301351822, language=EN, stringName=Chao YOU, firstName=Chao, middleName=null, lastName=YOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Transportation Science and Engineering, Civil Aviation University of China, Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885640477512596, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, authorId=1209885640301351822, language=CN, stringName=游超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 中国民航大学交通科学与工程学院, 天津 30030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885639953224575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, xref=2, ext=[AuthorCompanyExt(id=1209885639961613184, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639953224575, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Transportation Science and Engineering, Civil Aviation University of China, Tianjin 300300,China), AuthorCompanyExt(id=1209885639990973314, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639953224575, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民航大学交通科学与工程学院, 天津 30030)])]), Author(id=1209885640532038554, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, 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=1209885640620118943, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, authorId=1209885640532038554, language=EN, stringName=Cheng-yuan ZHU, firstName=Cheng-yuan, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209885640687227810, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, authorId=1209885640532038554, language=CN, stringName=朱承元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国民航大学空中交通管理学院, 天津 300300, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209885639873532794, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, xref=1, ext=[AuthorCompanyExt(id=1209885639881921404, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639873532794, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1209885639886115709, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639873532794, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学空中交通管理学院, 天津 300300)])])], keywords=[Keyword(id=1209885640854999974, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, orderNo=1, keyword=civil aviation transportation), Keyword(id=1209885640985023403, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, orderNo=2, keyword=flight delay prediction), Keyword(id=1209885641081492398, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, orderNo=3, keyword=Informer model), Keyword(id=1209885641165378482, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, orderNo=4, keyword=principal component analysis), Keyword(id=1209885641240875957, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, orderNo=5, keyword=neural networks), Keyword(id=1209885641299596216, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, orderNo=1, keyword=民航交通运输), Keyword(id=1209885641370899387, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, orderNo=2, keyword=航班延误预测), Keyword(id=1209885641438008252, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, orderNo=3, keyword=Informer模型), Keyword(id=1209885641584808894, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, orderNo=4, keyword=主成分分析), Keyword(id=1209885641664500673, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, orderNo=5, keyword=神经网络)], refs=[Reference(id=1209885644281745414, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=5, pageStart=980, pageEnd=990, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Alla H, Moumoun L, Balouki Y, journalName=Journal of Advances in Information Technology, refType=null, unstructuredReference=Alla H, Moumoun L, Balouki Y. Towards flight delays reduction: the effect of aircraft type and part of day on arrival delays prediction[J]. Journal of Advances in Information Technology, 2023, 14 (5): 980-990., articleTitle=Towards flight delays reduction: the effect of aircraft type and part of day on arrival delays prediction, refAbstract=null), Reference(id=1209885644403380232, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=15, issue=6, pageStart=740, pageEnd=753, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Li Q, Jing R Z, journalName=IET Intelligent Transport Systems, refType=null, unstructuredReference=Li Q, Jing R Z. Generation and prediction of flight delays in air transport[J]. IET Intelligent Transport Systems, 2021, 15 (6): 740-753., articleTitle=Generation and prediction of flight delays in air transport, refAbstract=null), Reference(id=1209885644495654923, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=6, pageStart=2533, pageEnd=2538, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=张兆宁, 张英杰, journalName=科学技术与工程, refType=null, unstructuredReference=张兆宁, 张英杰. 基于灰色聚类的大面积航班延误的延误程度评估[J]. 科学技术与工程, 2021, 21(6): 2533-2538., articleTitle=基于灰色聚类的大面积航班延误的延误程度评估, refAbstract=null), Reference(id=1209885644587929613, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=6, pageStart=2533, pageEnd=2538, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Zhang Zhaoning, Zhang Yingjie, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Zhaoning, Zhang Yingjie. Delay degree assessment of large-scale flight delays based on gray clustering[J]. Science Technology and Engineering, 2021, 21(6): 2533-2538., articleTitle=Delay degree assessment of large-scale flight delays based on gray clustering, refAbstract=null), Reference(id=1209885644696981520, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=7, pageStart=2749, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Ye B, Liu B, Tian Y, journalName=Sustainability, refType=null, unstructuredReference=Ye B, Liu B, Tian Y, et al. A methodology for predicting aggregate flight departure delays in airports based on supervised learning[J]. Sustainability, 2020, 12(7): 2749., articleTitle=A methodology for predicting aggregate flight departure delays in airports based on supervised learning, refAbstract=null), Reference(id=1209885644793450515, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=116, issue=null, pageStart=106822, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Guo Z, Yu B, Hao M Y, journalName=Aerospace Science and Technology, refType=null, unstructuredReference=Guo Z, Yu B, Hao M Y, et al. A novel hybrid method for flight departure delay prediction using random forest regression and maximal information coefficient[J]. Aerospace Science and Technology, 2021, 116: 106822., articleTitle=A novel hybrid method for flight departure delay prediction using random forest regression and maximal information coefficient, refAbstract=null), Reference(id=1209885644885725206, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=27, pageStart=11886, pageEnd=11891, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=李明捷, 黄欣宁, 吕晨辉, journalName=科学技术与工程, refType=null, unstructuredReference=李明捷, 黄欣宁, 吕晨辉, 等. 基于排队网络模型的机场航班延误预测[J]. 科学技术与工程, 2023, 23 (27): 11886-11891., articleTitle=基于排队网络模型的机场航班延误预测, refAbstract=null), Reference(id=1209885644965416984, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=27, pageStart=11886, pageEnd=11891, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Li Mingjie, Huang Xinning, Lü Chenhui, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Mingjie, Huang Xinning, Chenhui, et al. Airport flight delay prediction based on queuing network model[J]. Science Technology and Engineering, 2023, 23 (27): 11886-11891., articleTitle=Airport flight delay prediction based on queuing network model, refAbstract=null), Reference(id=1209885645078663194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=4, pageStart=1157, pageEnd=1173, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Dalmau R, journalName=CEAS Aeronautical Journal, refType=null, unstructuredReference=Dalmau R. Probabilistic and explainable tree-based models for rotational reactionary flight delay prediction[J]. CEAS Aeronautical Journal, 2024, 15(4): 1157-1173., articleTitle=Probabilistic and explainable tree-based models for rotational reactionary flight delay prediction, refAbstract=null), Reference(id=1209885645175132188, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=2, pageStart=197, pageEnd=209, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Muros G J A, Díaz O O, journalName=Journal of Airport Management, refType=null, unstructuredReference=Muros G J A, Díaz O O. Flight departure delay forecasting[J]. Journal of Airport Management, 2023, 17(2): 197-209., articleTitle=Flight departure delay forecasting, refAbstract=null), Reference(id=1209885645288378399, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=51, issue=5, pageStart=51, pageEnd=54, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=罗军, 李鹏飞, 罗凤娥, journalName=航空计算技术, refType=null, unstructuredReference=罗军, 李鹏飞, 罗凤娥. 基于ARIMA- BP神经网络的航班延误组合预测[J]. 航空计算技术, 2021, 51(5): 51-54, 59., articleTitle=基于ARIMA- BP神经网络的航班延误组合预测, refAbstract=null), Reference(id=1209885645359681570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=51, issue=5, pageStart=51, pageEnd=54, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Luo Jun, Li Pengfei, Luo Fenge, journalName=Aeronautical Computing Technology, refType=null, unstructuredReference=Luo Jun, Li Pengfei, Luo Fenge. Flight delay combination prediction based on ARIMA-BP neural network[J]. Aeronautical Computing Technology, 2021, 51(5): 51-54, 59., articleTitle=Flight delay combination prediction based on ARIMA-BP neural network, refAbstract=null), Reference(id=1209885645430984741, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=6, pageStart=847, pageEnd=854, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=丁建立, 孙玥, journalName=南京航空航天大学学报, refType=null, unstructuredReference=丁建立, 孙玥. 基于LightGBM的航班延误多分类预测[J]. 南京航空航天大学学报, 2021, 53(6): 847-854., articleTitle=基于LightGBM的航班延误多分类预测, refAbstract=null), Reference(id=1209885645548425257, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=6, pageStart=847, pageEnd=854, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=Ding Jianli, Sun Yue, journalName=Journal of Nanjing University of Aeronautics and Astronautics, refType=null, unstructuredReference=Ding Jianli, Sun Yue. Multi-class flight delay prediction based on LightGBM[J]. Journal of Nanjing University of Aeronautics and Astronautics, 2021, 53(6): 847-854., articleTitle=Multi-class flight delay prediction based on LightGBM, refAbstract=null), Reference(id=1209885645623922731, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2022, volume=472, issue=null, pageStart=280, pageEnd=293, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Shao W, Prabowo A, Zhao A, journalName=Neurocomputing, refType=null, unstructuredReference=Shao W, Prabowo A, Zhao A, et al. Predicting flight delay with spatio-temporal trajectory convolutional network and airport situational awareness map[J]. Neurocomputing, 2022, 472: 280-293., articleTitle=Predicting flight delay with spatio-temporal trajectory convolutional network and airport situational awareness map, refAbstract=null), Reference(id=1209885645716197421, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=10, pageStart=3275, pageEnd=3282, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=屈景怡, 杨柳, 陈旭阳, journalName=计算机应用, refType=null, unstructuredReference=屈景怡, 杨柳, 陈旭阳, 等. 基于时空序列的Conv-LSTM航班延误预测模型[J]. 计算机应用, 2022, 42(10): 3275-3282., articleTitle=基于时空序列的Conv-LSTM航班延误预测模型, refAbstract=null), Reference(id=1209885645833637936, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=10, pageStart=3275, pageEnd=3282, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=Qu Jingyi, Yang Liu, Chen Xuyang, journalName=Computer Applications, refType=null, unstructuredReference=Qu Jingyi, Yang Liu, Chen Xuyang, et al. Flight delay prediction model based on spatio-temporal sequence using Conv-LSTM[J]. Computer Applications, 2022, 42(10): 3275-3282., articleTitle=Flight delay prediction model based on spatio-temporal sequence using Conv-LSTM, refAbstract=null), Reference(id=1209885645904941106, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=8, pageStart=93, pageEnd=100, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=李善梅, 周相志, journalName=中国安全科学学报, refType=null, unstructuredReference=李善梅, 周相志. 基于S2S-CNN-GRU的机场离港航班延误预测[J]. 中国安全科学学报, 2023, 33(8): 93-100., articleTitle=基于S2S-CNN-GRU的机场离港航班延误预测, refAbstract=null), Reference(id=1209885645967855668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=8, pageStart=93, pageEnd=100, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Li Shanmei, Zhou Xiangzhi, journalName=China Safety Science Journal, refType=null, unstructuredReference=Li Shanmei, Zhou Xiangzhi. Departure flight delay prediction at airports based on S2S-CNN-GRU[J]. China Safety Science Journal, 2023, 33(8): 93-100., articleTitle=Departure flight delay prediction at airports based on S2S-CNN-GRU, refAbstract=null), Reference(id=1209885646039158839, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=238, issue=null, pageStart=121747, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=Maged M, Mostafa E, Hesham H, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Maged M, Mostafa E, Hesham H. Improving flight delays prediction by developing attention-based bidirectional LSTM network[J]. Expert Systems with Applications, 2024, 238: 121747., articleTitle=Improving flight delays prediction by developing attention-based bidirectional LSTM network, refAbstract=null), Reference(id=1209885646106267702, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=53, issue=6, pageStart=65, pageEnd=69, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=黄程, 王辉, 吴俊霖, journalName=航空计算技术, refType=null, unstructuredReference=黄程, 王辉, 吴俊霖, 等. 基于MHSA和C-BiGRU的航班延误预测研究[J]. 航空计算技术, 2023, 53(6): 65-69., articleTitle=基于MHSA和C-BiGRU的航班延误预测研究, refAbstract=null), Reference(id=1209885646177570873, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2023, volume=53, issue=6, pageStart=65, pageEnd=69, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=Huang Cheng, Wang Hui, Wu Junlin, journalName=Aeronautical Computing Technology, refType=null, unstructuredReference=Huang Cheng, Wang Hui, Wu Junlin, et al. Research on flight delay prediction based on MHSA and C-BiGRU[J]. Aeronautical Computing Technology, 2023, 53(6): 65-69., articleTitle=Research on flight delay prediction based on MHSA and C-BiGRU, refAbstract=null), Reference(id=1209885646236291129, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=247, issue=null, pageStart=123306, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=Bisandu B D, Moulitsas I, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Bisandu B D, Moulitsas I. Prediction of flight delay using deep operator network with gradient-mayfly optimisation algorithm[J]. Expert Systems with Applications, 2024, 247: 123306., articleTitle=Prediction of flight delay using deep operator network with gradient-mayfly optimisation algorithm, refAbstract=null), Reference(id=1209885646299205691, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=12, pageStart=11106, pageEnd=11115, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=Zhou H, Zhang S, Peng J, journalName=Proceedings of the AAAI Conference on Artificial Intelligence, refType=null, unstructuredReference=Zhou H, Zhang S, Peng J, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(12): 11106-11115., articleTitle=Informer: beyond efficient transformer for long sequence time-series forecasting, refAbstract=null), Reference(id=1209885646378897470, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=310, issue=null, pageStart=133290, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=Cui S, Lü S, Ma Y, journalName=Energy, refType=null, unstructuredReference=Cui S, S, Ma Y, et al. Corrigendum to “improved informer PV power short-term prediction modelbased on weather typing and AHA-VMD-MPE”[J]. Energy, 2024, 310: 133290., articleTitle=Corrigendum to “improved informer PV power short-term prediction modelbased on weather typing and AHA-VMD-MPE”, refAbstract=null), Reference(id=1209885646441812033, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=19, issue=3, pageStart=98, pageEnd=106, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=聂靖杰, 刘树鑫, 邢朝健, journalName=电气工程学报, refType=null, unstructuredReference=聂靖杰, 刘树鑫, 邢朝健, 等. 基于TPE-Informer模型的铁路继电器寿命预测[J]. 电气工程学报, 2024, 19(3): 98-106., articleTitle=基于TPE-Informer模型的铁路继电器寿命预测, refAbstract=null), Reference(id=1209885646529892420, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=19, issue=3, pageStart=98, pageEnd=106, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=Nie Jingjie, Liu Shuxin, Xing Chaojian, journalName=Journal of Electrical Engineering, refType=null, unstructuredReference=Nie Jingjie, Liu Shuxin, Xing Chaojian, et al. Life prediction of railroad relays based on TPE-Informer model[J]. Journal of Electrical Engineering, 2024, 19(3): 98-106., articleTitle=Life prediction of railroad relays based on TPE-Informer model, refAbstract=null), Reference(id=1209885646634750023, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=13, url=http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html, language=null, rfNumber=[20], rfOrder=27, authorNames=覃文文, 彭栋梁, 戢晓峰, journalName=交通运输系统工程与信息, refType=null, unstructuredReference=覃文文, 彭栋梁, 戢晓峰, 等. 山区双车道公路借道超车轨迹预测模型[J]. 交通运输系统工程与信息, 1-13[2025-03-25]. http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html., articleTitle=山区双车道公路借道超车轨迹预测模型, refAbstract=null), Reference(id=1209885646718636105, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=13, url=http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html, language=null, rfNumber=[20], rfOrder=28, authorNames=Qin Wenwen, Peng Dongliang, Ji Xiaofeng, journalName=Transportation Systems Engineering and Information, refType=null, unstructuredReference=Qin Wenwen, Peng Dongliang, Ji Xiaofeng, et al. Trajectory prediction model for borrowed overtaking on two-lane highways in mountainous areas[J]. Transportation Systems Engineering and Information, 1-13[2025-03-25].http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html., articleTitle=Trajectory prediction model for borrowed overtaking on two-lane highways in mountainous areas, refAbstract=null), Reference(id=1209885646806716493, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=5220, pageEnd=5226, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=张兆宁, 查子奇, journalName=科学技术与工程, refType=null, unstructuredReference=张兆宁, 查子奇. 基于多机场终端区交通态势的航班延误预测[J]. 科学技术与工程, 2024, 24(12): 5220-5226., articleTitle=基于多机场终端区交通态势的航班延误预测, refAbstract=null), Reference(id=1209885646915768400, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=5220, pageEnd=5226, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=Zhang Zhaoning, Cha Ziqi, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Zhaoning, Cha Ziqi. Flight delay prediction based on traffic dynamics in multi-airport terminalareas[J]. Science Technology and Engineering, 2024, 24(12): 5220-5226., articleTitle=Flight delay prediction based on traffic dynamics in multi-airport terminalareas, refAbstract=null), Reference(id=1209885646999654482, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=4, pageStart=1434, pageEnd=1441, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=韩博, 林师卓, 王立婕, journalName=安全与环境学报, refType=null, unstructuredReference=韩博, 林师卓, 王立婕. 机场能见度临近预测方法[J]. 安全与环境学报, 2024, 24(4): 1434-1441., articleTitle=机场能见度临近预测方法, refAbstract=null), Reference(id=1209885647091929170, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=4, pageStart=1434, pageEnd=1441, url=null, language=null, rfNumber=[22], rfOrder=32, authorNames=Han Bo, Lin Shizhuo, Wang Lijie, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=Han Bo, Lin Shizhuo, Wang Lijie. Near-term prediction method for airport visibility[J]. Journal of Safety and Environment, 2024, 24(4): 1434-1441., articleTitle=Near-term prediction method for airport visibility, refAbstract=null)], funds=[Fund(id=1209885644109778947, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, awardId=U2133207, language=CN, fundingSource=国家自然科学基金民航联合基金重点项目(U2133207), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1209885639873532794, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, xref=1, ext=[AuthorCompanyExt(id=1209885639881921404, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639873532794, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1209885639886115709, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639873532794, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学空中交通管理学院, 天津 300300)]), AuthorCompany(id=1209885639953224575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, xref=2, ext=[AuthorCompanyExt(id=1209885639961613184, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639953224575, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Transportation Science and Engineering, Civil Aviation University of China, Tianjin 300300,China), AuthorCompanyExt(id=1209885639990973314, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, companyId=1209885639953224575, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民航大学交通科学与工程学院, 天津 30030)])], figs=[ArticleFig(id=1209885641886798789, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.1, caption=Schematic diagram of Informer model structure, figureFileSmall=Bk3xT2nj+rDBu5hwovLszg==, figureFileBig=qT59Yo8mnILAk2/90oI/eQ==, tableContent=null), ArticleFig(id=1209885641953907655, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图1, caption=Informer模型结构示意图, figureFileSmall=Bk3xT2nj+rDBu5hwovLszg==, figureFileBig=qT59Yo8mnILAk2/90oI/eQ==, tableContent=null), ArticleFig(id=1209885642079736779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.2, caption=Overall framework for flight delay prediction, figureFileSmall=xMFxLRjXSKtOtMjvYqjvwQ==, figureFileBig=J0ChBsqbAgBUsf5Lr40opA==, tableContent=null), ArticleFig(id=1209885642163622861, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图2, caption=航班延误预测整体框架, figureFileSmall=xMFxLRjXSKtOtMjvYqjvwQ==, figureFileBig=J0ChBsqbAgBUsf5Lr40opA==, tableContent=null), ArticleFig(id=1209885642230731727, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.3, caption=ATL january 2023 first ten days of delay statistics, figureFileSmall=jTxdZ3bQzcKzTMRSoHKePg==, figureFileBig=fVIJZafaqgmGbispjcVL2Q==, tableContent=null), ArticleFig(id=1209885642314617809, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图3, caption=ATL2023年1月前十天延误统计, figureFileSmall=jTxdZ3bQzcKzTMRSoHKePg==, figureFileBig=fVIJZafaqgmGbispjcVL2Q==, tableContent=null), ArticleFig(id=1209885642377532372, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.4, caption=Feature correlation analysis, figureFileSmall=oZ+4wLbBnlb42eA/sYKG0g==, figureFileBig=j+d/0b5JQ4n3ZaKONV5GQA==, tableContent=null), ArticleFig(id=1209885642440446934, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图4, caption=特征相关性分析, figureFileSmall=oZ+4wLbBnlb42eA/sYKG0g==, figureFileBig=j+d/0b5JQ4n3ZaKONV5GQA==, tableContent=null), ArticleFig(id=1209885642524333016, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.5, caption=Different model input evaluation indicators, figureFileSmall=88WGcZyicFxT269CB3rPLg==, figureFileBig=nX3WJfBmW4c76rLNfaTeAw==, tableContent=null), ArticleFig(id=1209885642612413402, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图5, caption=不同模型输入评价指标, figureFileSmall=88WGcZyicFxT269CB3rPLg==, figureFileBig=nX3WJfBmW4c76rLNfaTeAw==, tableContent=null), ArticleFig(id=1209885642729853918, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.6, caption=Comparison of predicted and true values of different models, figureFileSmall=7J+b48Vc6RvoHmwzQ9ZG5g==, figureFileBig=xYvjDsH2tYehR65ZRdfIrQ==, tableContent=null), ArticleFig(id=1209885642813740001, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图6, caption=不同模型预测值与真实值对比, figureFileSmall=7J+b48Vc6RvoHmwzQ9ZG5g==, figureFileBig=xYvjDsH2tYehR65ZRdfIrQ==, tableContent=null), ArticleFig(id=1209885642914403298, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.7, caption=Comparison of predicted and true values for 1~4 h prediction step, figureFileSmall=tIXA6QTnwfYsUUTuQGNWrg==, figureFileBig=3K4XxI6AWsjNLHynOps8xg==, tableContent=null), ArticleFig(id=1209885642981512165, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图7, caption=1~4 h预测步长预测值与真实值对比, figureFileSmall=tIXA6QTnwfYsUUTuQGNWrg==, figureFileBig=3K4XxI6AWsjNLHynOps8xg==, tableContent=null), ArticleFig(id=1209885643069592552, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Fig.8, caption=Violin box line plot of 1~4 h predicted residual values, figureFileSmall=f8f8TqLMEeZWFs9DW7YaVQ==, figureFileBig=E9tlaAGhVDCBVf5ncd/mow==, tableContent=null), ArticleFig(id=1209885643149284331, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=图8, caption=1~4 h预测残差值小提琴箱线图, figureFileSmall=f8f8TqLMEeZWFs9DW7YaVQ==, figureFileBig=E9tlaAGhVDCBVf5ncd/mow==, tableContent=null), ArticleFig(id=1209885643220587501, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Table 1, caption=

Principal component loading matrix

, figureFileSmall=null, figureFileBig=null, tableContent=
特征 主成分1 主成分2 主成分3 主成分4
观测高度 -0.55 -0.13 0.21 -0.02
露点温度 0.39 -0.24 -0.20 -0.15
降水量 0.16 -0.11 0.55 0.02
压力趋势 0.05 -0.02 -0.07 0.74
相对湿度 0.32 -0.40 0.19 -0.07
观测气压 -0.55 -0.14 0.21 -0.01
能见度 -0.22 0.21 -0.55 0.08
阵风速度 0.09 0.45 0.33 0.16
风速 -0.20 0.52 0.29 0.06
风向 0.15 0.38 -0.12 -0.10
流量 0.26 0.24 0.16 0.60
), ArticleFig(id=1209885643291890671, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=表1, caption=

主成分载荷矩阵

, figureFileSmall=null, figureFileBig=null, tableContent=
特征 主成分1 主成分2 主成分3 主成分4
观测高度 -0.55 -0.13 0.21 -0.02
露点温度 0.39 -0.24 -0.20 -0.15
降水量 0.16 -0.11 0.55 0.02
压力趋势 0.05 -0.02 -0.07 0.74
相对湿度 0.32 -0.40 0.19 -0.07
观测气压 -0.55 -0.14 0.21 -0.01
能见度 -0.22 0.21 -0.55 0.08
阵风速度 0.09 0.45 0.33 0.16
风速 -0.20 0.52 0.29 0.06
风向 0.15 0.38 -0.12 -0.10
流量 0.26 0.24 0.16 0.60
), ArticleFig(id=1209885643388359665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Table 2, caption=

Comparison of input errors of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
误差 不同模型输入对比
Informer CA-Informer PCA-Informer CA-PCA-
Informer
MAE 7.398 4 7.044 7 6.726 8 6.342 1
RMSE 17.847 7 17.556 7 17.147 7 16.829 2
), ArticleFig(id=1209885643497411573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=表2, caption=

不同模型输入误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
误差 不同模型输入对比
Informer CA-Informer PCA-Informer CA-PCA-
Informer
MAE 7.398 4 7.044 7 6.726 8 6.342 1
RMSE 17.847 7 17.556 7 17.147 7 16.829 2
), ArticleFig(id=1209885643589686264, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Table 3, caption=

Comparison of errors of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
误差 不同模型对比
CA-PCA-LSTM CA-PCA-GRU CA-PCA-Informer
MAE 7.997 7 7.951 9 6.342 1
RMSE 18.973 9 19.585 8 16.829 2
), ArticleFig(id=1209885643719709692, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=表3, caption=

不同模型误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
误差 不同模型对比
CA-PCA-LSTM CA-PCA-GRU CA-PCA-Informer
MAE 7.997 7 7.951 9 6.342 1
RMSE 18.973 9 19.585 8 16.829 2
), ArticleFig(id=1209885643807790079, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=EN, label=Table 4, caption=

Comparison of errors for different prediction steps

, figureFileSmall=null, figureFileBig=null, tableContent=
误差 不同预测步长对比
1 h 2 h 3 h 4 h
MAE 6.342 1 7.427 1 8.523 6 9.650 6
RMSE 16.829 2 17.165 5 18.340 2 18.602 8
), ArticleFig(id=1209885643925229570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209819471896768602, language=CN, label=表4, caption=

不同预测步长误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
误差 不同预测步长对比
1 h 2 h 3 h 4 h
MAE 6.342 1 7.427 1 8.523 6 9.650 6
RMSE 16.829 2 17.165 5 18.340 2 18.602 8
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405116, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405116, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405116, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405116, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于Informer模型的航班延误预测
收藏切换
PDF下载
杨新湦 1 , 游超 2 , 朱承元 1
科学技术与工程 | 论文∙航空、航天 2025,25(19): 8282-8288
收起
收藏切换
科学技术与工程 | 论文∙航空、航天 2025, 25(19): 8282-8288
基于Informer模型的航班延误预测
全屏
杨新湦1 , 游超2, 朱承元1
作者信息
  • 1 中国民航大学空中交通管理学院, 天津 300300
  • 2 中国民航大学交通科学与工程学院, 天津 30030
  • 杨新湦( 1966—),男,汉族,陕西扶风人,硕士,教授。研究方向:交通运输规划与管理。E-mail:

Flight Delay Prediction Based on Informer Modeling
Xin-sheng YANG1 , Chao YOU2, Cheng-yuan ZHU1
Affiliations
  • 1 School of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China
  • 2 School of Transportation Science and Engineering, Civil Aviation University of China, Tianjin 300300,China
出版时间: 2025-07-08 doi: 10.12404/j.issn.1671-1815.2405116
文章导航
收藏切换
为能更加精准预测不同时段的航班延误态势,选用美国亚特兰大机场2023年全年的运行数据与相关气象数据进行实验,提出基于相关系分析(correlation analysis,CA),主成分分析(principal components analysis,PCA)和Informer模型的CA-PCA-Informer航班延误预测模型,采用MAE(mean absolute error)和RMSE(root mean square error)作为模型的评价指标进行预测误差分析。结果表明,CA-PCA-Informer模型比简单的组合模型预测效果更好,与CA-PCA-LSTM和CA-PCA-GRU模型相比模型误差最低,MAE和RMSE分别降低了20.2%~20.7%和12.7%~14.1%;CA-PCA-Informer模型对预测步长为1 h时预测更为精准,该模型可以为决策者提供更加准确的航班延误态势以保证航班的高效运行。
民航交通运输  /  航班延误预测  /  Informer模型  /  主成分分析  /  神经网络

In order to more accurately predict flight delays at different times of the year,flight delay prediction trends was investigated using operational and meteorological data from Atlanta Airport in the United States for the year 2023. A CA-PCA-Informer flight delay prediction model,incorporating correlation analysis (CA),principal component analysis (PCA),and the Informer model,was proposed. Mean absolute error (MAE) and root mean square error (RMSE) were utilized as evaluation metrics to assess the prediction error. The findings reveal that the CA-PCA-Informer model outperforms simpler combined models,demonstrating the lowest error compared to the CA-PCA-LSTM and CA-PCA-GRU models,with MAE and RMSE reductions of 20.2%~20.7% and 12.7%~14.1%,respectively. The CA-PCA-Informer model is particularly effective for one-hour ahead predictions,providing decision-makers with more accurate flight delay trends to enhance efficient flight operations.

civil aviation transportation  /  flight delay prediction  /  Informer model  /  principal component analysis  /  neural networks
杨新湦, 游超, 朱承元. 基于Informer模型的航班延误预测. 科学技术与工程, 2025 , 25 (19) : 8282 -8288 . DOI: 10.12404/j.issn.1671-1815.2405116
Xin-sheng YANG, Chao YOU, Cheng-yuan ZHU. Flight Delay Prediction Based on Informer Modeling[J]. Science Technology and Engineering, 2025 , 25 (19) : 8282 -8288 . DOI: 10.12404/j.issn.1671-1815.2405116
随着中国经济的不断增长,交通运输量逐年上涨,民航的出行需求加大,导致航班延误问题越来越多[1-2]。航班延误不仅会造成旅客不愉快的乘机体验,导致航空公司和机场名誉受损,也会给机场和空管对航班正常运行的管控造成影响。因此,为减少造成不必要的损失,对航班延误进行有效的预测具有十分重要的研究意义。
航班延误预测方法一直是国内外学者们研究的热点问题,首先是传统统计学方法以及线性回归、决策树等传统机器学习算法。张兆宁等[3]建立了灰色综合聚类评估模型评估大面积航班延误程度。Ye等[4]同时采用了多元线性回归研究了机场的起飞延误。Guo等[5]提出了一种随机森林回归与最大信息系数混合的航班起飞延误预测方法,李明捷等[6]采用Lempel-Ziv算法求解了机场排队网络延误模型。Dalmall[7]结合自然梯度增强和特征归因方法预测了单个航班的反应延迟。
随着计算机方法的发展,深度学习方法因为能更为优秀地处理海量数据而备受学者们的青睐,使用深度学习的方法展开的航班延误预测越来越多[8]。罗军等[9]提出了基于自动回归平均和BP(back propagation)神经网络的组合预测模型,提高了航班延误的预测精度;丁建立等[10]使用了LightGBM(light gradient boosting machine)模型对航班延误进行了多分类预测,该模型与其他模型相比大幅降低了训练时间成本并提升了预测精。Shao等[11]提出了一种端到端的深度学习架构TrajCNN(trajectory convolutional neural network),同时捕获航班起飞延误的时空信息。屈景怡[12]提出了考虑时空序列的Conv-LSTM(convolutional long short-term memory)模型,并基于模型设计了基于B/S的延误分析系统;李善梅等[13]提出了一种序列到序列的CNN-GRU(gated recurrent unit)的离港航班延误预测模型;Maged等[14]提出了一种基于注意力的双向长短期记忆框架集成网络,并基于此开发了实时高精度延误预测系统,黄程等[15]提出了基于多头注意力机制和卷积双向门控循环单元的航班延误预测模型,并验证了该模型能捕获特征中更重要的信息。Bisandu等[16]使用Gradient Mayfly优化算法与DeepONet相结合来预测航班延误。近年来,针对时间序列预测问题,由Transformer改进的Informer模型[17]凭借独有的Probsparse自注意力机制降低了计算复杂度,通过蒸馏操作大幅减少了计算资源的浪费,相较于传统方法提高了预测的准确性和高效性。该模型在风电功率、电器寿命以及车辆轨迹等[18-20]研究领域均有较为广泛的应用,验证了其正确性和实用性。
综上所述,在研究对象层面,以往对于航班延误的研究对象将重点放在个体航班的延误上,评价的是单个航班的延误情况,文中将固定时间段的航班集和的航班延误作为研究主体,以更好地捕捉不同时段航班集的航班延误的总态势和变化趋势。在方法层面,现有的深度学习方法主要集中在长短时记忆网络的组合算法上,缺乏Informer相关模型在航班延误预测问题中的应用。因此,根据过往的航班数据与气象数据,统计其时段延误情况并进行研究,以期实现对一定时间段内的航班延误时间进行准确预测。
不同时段影响延误时间的主要因素为本时段航班流量以及对应的天气状况[21],文中主要采用的是美国亚特兰大机场2023全年的气象数据以及航班运行数据。相关天气数据来源为美国国家海洋和大气管理局(National Oceanic and Atmospheric Administration,NOAA),相关历史航班数据来源为美国交通统计局(the Bureau of Transportation Statistics,BTS)。其中,航班数据主要包括日期、航班号、始发机场、计划起飞时间,实际出发时间、目的地机场、计划到达时间、实际到达时间等8个属性,天气数据包括露点温度、风速、风向、湿度、气压、能见度、降水量等10个属性。
航班原始数据集存在极小部分的空值和异常值。通过航班数据计算每个航班的延误时间,对于到港航班,计算公式为延误时间=实际到达时间-计划到达时间;对于离港航班,计算公式为延误时间=实际起飞时间-计划起飞时间,负值代表提前到达,统计为0。天气原始数据中存在少部分缺失,文中对于大部分连续类型数据,采用线性插值发进行填充;对于风向中VRB(variable wind direction)等离散随机数据采用随机森林的方法对数据集进行修复[22],随机森林通过集成多棵决策树的预测结果来填补缺失值,利用每棵树的预测能力,从而提高填补的准确性和鲁棒性。通过编写python程序实现,其主要步骤如下:
(1)读取原始数据集。
(2)将不包含缺失值的行用于训练模型。
(3)引入python中的sklearn RandomForestRegressor包训练随机森林模型。
(4)预测缺失值并进行填充。
得到航班和天气的完整数据集后,对运行和天气数据集进行融合,以时间为融合的主键,将每个时间段和气象的观测时间进行关联,得到融合后用于模型输入的数据集。
相关性分析(correlation analysis,CA)常用来衡量数据之间的相关性,相关性分析采用的是皮尔逊相关系数r,常用于度量两个变量之间的相关程度,其计算公式为
$r=\frac{\sum_{i=1}^{n}\left(X_{i}-\bar{X}\right)\left(Y_{i}-\bar{Y}\right)}{\sqrt{\sum_{i=1}^{n}\left(X_{i}-\bar{X}\right)^{2}} \sqrt{\sum_{i=1}^{n}\left(Y_{i}-\bar{Y}\right)^{2}}}$
式(1)中: X ¯ Y ¯为样本均值; X i Y i为样本点。
主成分分析法是一种常用的数据降维方法,其核心思想是通过线性变换,将数据投影到新的坐标系中,使得投影后的数据在新坐标系中的方差最大化,新坐标系的指标被称为主成分,将主成分作为模型的输入,可以很好地提升模型的预测效果。其主要步骤如下:
(1)数据标准化。每个特征减去其均值,再除以其标准差,得到零均值、单位方差的标准化数据。
(2)计算协方差矩阵。通过标准化后的数据计算协方差矩阵,反映各特征之间的线性关系。
(3)特征值分解。对协方差矩阵进行特征值分解,得到特征值和特征向量。
(4)选择主成分。根据特征值的大小选择前 k个最大的特征值对应的特征向量,作为主成分。选择的原则是保留尽可能多的方差信息。
(5)投影到主成分空间。将原始数据投影到选定的主成分空间,得到降维后的数据。新的主成分空间表示为
Z = X ' V k
式(2)中: X '为标准化后的数据;Vk为选定的k个主成分的特征向量矩阵;Z为投影后的数据。
Infomer模型是一种基于Transformer的进行改进的模型,针对Transformer在时间序列预测中遇到的自注意力机制的二次时间复杂度等问题,提出了概率稀疏自注意力机制,降低了运算的时间复杂度,其时间复杂度为O(NlnN);针对堆叠导致的内存瓶颈问题,提出了注意力蒸馏操作对特征进行压缩;使用生成式解码方式进一步提高了模型的预测速度,其结构如图1所示。
Transformer中提出的自注意力机制是通过使用查询Q(Query)、键K(Key)和值V(Value)来计算序列中各个元素之间的相关性,公式为
A ( Q , K , V ) = S o f t m a x Q K T d V
式(3)中: Q R L Q × d K R L K × d V R L V × d;d为输入序列的维度;LQLKLV分别为查询、键、值的矩阵维度。
概率稀疏自注意力机制是以概率稀疏化自注意力矩阵,将时间复杂度降低至对数的线性复杂度,其第iQ的注意力系数通过概率p的形式定义为
A ( q i , K , V ) = j k ( q i , k j ) l k ( q i , k l ) v j = E p ( k j | q i ) [ v j ]
式(4)中: p ( q i , k j )= k ( q i , k j ) l k ( q i , k l );E为期望;p为条件概率; q i表示Q矩阵第i行; k j v j表示K矩阵和V矩阵的第j行。
为了量化查询相邻的稀缺性,使用了KL(Kullback-Leibler)散度计算Q向量的概率分布与均匀分布的熵,其中第i个稀疏性度量的定义式为
M ( q i , K ) = l n j = 1 L K e q j k T j d - 1 L K j = 1 L K q i k T j d
由此,概率稀疏注意力机制可表示为
A ( Q , K , V ) = S o f t m a x ( Q ¯ K T d ) V
式(6)中: Q ¯为经过上述概率稀疏度量得到的。
针对长序列存在的输入之间的长范围依赖,通过注意力蒸馏机制在内存有限的情况下将单个层级特征时间维度减半,蒸馏机制是采用一维卷积以及最大池化对时间维度进行下采样,从d层到d+1层计算公式为
X d + 1 t = M a x P o o l { E L U [ C o n v l d ( [ X d t ] A B ) ] }
式(7)中: [ X d t ] A B为多头概率稀疏自注意力机制的关键步骤;Convld为一维卷积操作;ELU为激活函数;MaxPool为最大池化操作。蒸馏操作对每一层数序列长度都逐层减半,减少了计算的内存使用。
Informer采用生成式的一步Decoder,如图1所示,由遮挡的多头注意力机制和遮挡的多头稀疏注意力机制组成,通过掩码操作遮挡多头注意力,避免了模型的自回归现象。
该Decoder的输入为
X D E t = C o n c a t ( X t o k e n t , X 0 t ) R ( L t o k e n + L y ) × d m o d e l
式(8)中: X D E t为学习输入的序列; X t o k e n t为已知标签序列; X 0 t为结果的占位符。
由于航班平均延误时间往往会受流量和天气状况的影响,且流量、天气状况和平均延误时间之间存在复杂的关系,为能捕捉这种非线性的关系,文中提出了一种基于CA-PCA-Informer的航班延误预测模型,首先对数据集进行相关性分析,剔除冗余特征,然后通过PCA对剩余特征进行降维并保留重要信息,最后使用Informer模型对数据集进行训练预测,其框架如图2所示,具体步骤如下:
(1)收集相关航空运行数据与天气数据。
(2)对数据集进行预处理,并对数据特征进行相关性分析,删除相关性大于0.9的特征。
(3)将剩余的特征归一化,使用PCA对特征进行降维处理。
(4)将得到的主成分因子作为新的数据集作为Informer模型的输入,对得到预测结果进行分析。
为了更直观的对比不同时间窗口以及不同模型的结果,选择平均绝对误差和均方根误差作为评价指标。MAE计算误差的绝对值,易于理解且不受异常值影响;RMSE通过平方误差强调较大误差,敏感于异常值,反映预测的稳定性。其计算公式为
M A E = 1 n i = 1 n | y i ¯ - y i |
R M S E = 1 n i = 1 n ( y i ¯ - y i ) 2
式中:n为样本总数; y i ¯为模型预测值; y i为对应的真实值。
对预处理好的航班延误数据进行统计,选取美国亚特兰大机场2023年1月前十天的航班延误数据,对其变化特征进行分析,结果如图3所示,可知每天的延误情况呈现非线性的周期性规律,亚特兰大机场的延误重灾时间段主要集中在每天的晚上10点到凌晨2点左右,考虑到该时段流量较小,这种延误大概率是天气等特殊原因造成的。
相关性分析结果如图4所示,颜色越深代表两者的相关性越强,露点温度,干球温度与湿球温度相关性过高,删除干球温度和湿球温度,海平面气压与气压相关性过高,删除海平面气压,流量与平均延误时间存在正相关性,其余特征与平均延误时间之间有一定相关性,且这种相关性不可忽略。
使用Python对上述剩下的11个特征使用主成分分析法进行处理计算,结果表明,主成分1、2、3和4的贡献率分别为24.12%、18.73%、12.15%和10.58%,累计贡献率达到了65.58%,其余主成分贡献率均在10%以下,可以认为这四个变量足以解释原始变量信息。主成分载荷矩阵见表1,在载荷矩阵中,流量与平均延误时间之间存在正相关,即主成分包含了原数据集的关键信息,主成分能够保留其作为模型的输入。
原始数据集共有8 760条数据,按照数量比划分训练集,验证集和测试集为7∶1∶2,将原始数据集,以及优化后的数据集作为模型不同的输入进行实验。
实验采用的操作系统为Windows11系统,CPU为AMDRyzen7-5800H,运行内存16 G,GPU为NVIDIA GeForce RTX 3060laptop 6G,实验的环境配置为Python 3.6.10、Tensorflow 2.6.2、Keras 2.6.0、pandas 1.1.5。
对模型进行纵向对比,测试不同模型输入对模型的影响,采用原始数据集,CA优化后的数据集,PCA优化后的数据集以及CA和PCA共同优化后的数据集,以检验CA-PCA-Informer模型的精度,其测试集结果见表2图5。其中CA-PCA-Informer模型的MAE以及MRSE为6.342 1和16.829 2,相比其他组合模型,CA-PCA-Informer模型误差最低,相比Informer模型的MAE和RMSE分别降低了1.056 3和1.018 5;相比CA-Informer模型分别降低了0.702 6和0.727 3;相比PCA-Informer模型分别降低了0.384 8和0.318 5。其结果表明,经过相关性分析和主成分分析后,消除了部分数据集的冗杂信息,提高了Informer模型的预测能力。
对模型进行横向对比,采用CA-PCA-LSTM,CA-PCA-GRU和CA-PCA-Informer进行实验。在同一数据集上对比LSTM,GRU和Informer模型的预测性能,以验证CA-PCA-Informer模型在处理长时间序列上的优势,其测试集结果见表3。由表3可知,CA-PCA-Informer模型误差最小,与CA-PCA-LSTM模型相比,MAE和RMSE分别降低了1.655 6和2.144 7;与CA-PCA-GRU模型相比,MAE和RMSE分别降低了1.609 8和2.756 6,证明Informer模型在长时间序列预测上效果更好。由图6可知CA-PCA-Informer模型预测值更接近于真实值。
对模型的预测步长进行研究,使用CA-PCA-Informer模型分别研究1、2、3、4 h预测步长的模型预测能力,其测试集误差结果见表4
预测步长为1 h时模型预测误差最低,相比预测步长为2 h时MAE和RMSE分别降低了1.085和0.336 3;相比预测步长为3 h时MAE和RMSE分别降低了2.181 5和1.511;相比预测步长为4 h时MAE和RMSE分别降低了3.308 5和1.773 6。由图7可以看出,随着预测步长的加大,模型的预测能力有所下降,与真实值的差距逐渐增大。图8所示为1~4 h预测残差值的小提琴箱线图,可以看出预测步长为1 h时,相对其他的预测步长的数据残差集中于较小值,异常值更小,预测效果最好。
(1)通过比较原始数据,CA和PCA优化后的数据作为Informer模型输入的效果,CA-PCA-Informer模型的误差最小,模型的MAE和RMSE分别为6.342 1和16.829 2,证明经过相关性分析和主成分分析优化后的模型输入预测效果更优。
(2)通过分别与CA-PCA-LSTM和CA-PCA-GRU模型对比,证明了CA-PCA-Informer模型更能捕捉长时间序列的变化趋势,在模型的预测性能上更优。
(3)通过对比1~4 h预测步长的CA-PCA-Informer模型的预测能力,证明了模型对于1 h预测步长的平均延误时间预测最精准,随着预测步长的增加,模型的性能虽有所下降,但RMSE变化不大,证明CA-PCA-Informer模型预测具有稳定性。
  • 国家自然科学基金民航联合基金重点项目(U2133207)
参考文献 引证文献
排序方式:
[1]
Alla H, Moumoun L, Balouki Y. Towards flight delays reduction: the effect of aircraft type and part of day on arrival delays prediction[J]. Journal of Advances in Information Technology, 2023, 14 (5): 980-990.
[2]
Li Q, Jing R Z. Generation and prediction of flight delays in air transport[J]. IET Intelligent Transport Systems, 2021, 15 (6): 740-753.
[3]
张兆宁, 张英杰. 基于灰色聚类的大面积航班延误的延误程度评估[J]. 科学技术与工程, 2021, 21(6): 2533-2538.
Zhang Zhaoning, Zhang Yingjie. Delay degree assessment of large-scale flight delays based on gray clustering[J]. Science Technology and Engineering, 2021, 21(6): 2533-2538.
[4]
Ye B, Liu B, Tian Y, et al. A methodology for predicting aggregate flight departure delays in airports based on supervised learning[J]. Sustainability, 2020, 12(7): 2749.
[5]
Guo Z, Yu B, Hao M Y, et al. A novel hybrid method for flight departure delay prediction using random forest regression and maximal information coefficient[J]. Aerospace Science and Technology, 2021, 116: 106822.
[6]
李明捷, 黄欣宁, 吕晨辉, 等. 基于排队网络模型的机场航班延误预测[J]. 科学技术与工程, 2023, 23 (27): 11886-11891.
Li Mingjie, Huang Xinning, Chenhui, et al. Airport flight delay prediction based on queuing network model[J]. Science Technology and Engineering, 2023, 23 (27): 11886-11891.
[7]
Dalmau R. Probabilistic and explainable tree-based models for rotational reactionary flight delay prediction[J]. CEAS Aeronautical Journal, 2024, 15(4): 1157-1173.
[8]
Muros G J A, Díaz O O. Flight departure delay forecasting[J]. Journal of Airport Management, 2023, 17(2): 197-209.
[9]
罗军, 李鹏飞, 罗凤娥. 基于ARIMA- BP神经网络的航班延误组合预测[J]. 航空计算技术, 2021, 51(5): 51-54, 59.
Luo Jun, Li Pengfei, Luo Fenge. Flight delay combination prediction based on ARIMA-BP neural network[J]. Aeronautical Computing Technology, 2021, 51(5): 51-54, 59.
[10]
丁建立, 孙玥. 基于LightGBM的航班延误多分类预测[J]. 南京航空航天大学学报, 2021, 53(6): 847-854.
Ding Jianli, Sun Yue. Multi-class flight delay prediction based on LightGBM[J]. Journal of Nanjing University of Aeronautics and Astronautics, 2021, 53(6): 847-854.
[11]
Shao W, Prabowo A, Zhao A, et al. Predicting flight delay with spatio-temporal trajectory convolutional network and airport situational awareness map[J]. Neurocomputing, 2022, 472: 280-293.
[12]
屈景怡, 杨柳, 陈旭阳, 等. 基于时空序列的Conv-LSTM航班延误预测模型[J]. 计算机应用, 2022, 42(10): 3275-3282.
Qu Jingyi, Yang Liu, Chen Xuyang, et al. Flight delay prediction model based on spatio-temporal sequence using Conv-LSTM[J]. Computer Applications, 2022, 42(10): 3275-3282.
[13]
李善梅, 周相志. 基于S2S-CNN-GRU的机场离港航班延误预测[J]. 中国安全科学学报, 2023, 33(8): 93-100.
Li Shanmei, Zhou Xiangzhi. Departure flight delay prediction at airports based on S2S-CNN-GRU[J]. China Safety Science Journal, 2023, 33(8): 93-100.
[14]
Maged M, Mostafa E, Hesham H. Improving flight delays prediction by developing attention-based bidirectional LSTM network[J]. Expert Systems with Applications, 2024, 238: 121747.
[15]
黄程, 王辉, 吴俊霖, 等. 基于MHSA和C-BiGRU的航班延误预测研究[J]. 航空计算技术, 2023, 53(6): 65-69.
Huang Cheng, Wang Hui, Wu Junlin, et al. Research on flight delay prediction based on MHSA and C-BiGRU[J]. Aeronautical Computing Technology, 2023, 53(6): 65-69.
[16]
Bisandu B D, Moulitsas I. Prediction of flight delay using deep operator network with gradient-mayfly optimisation algorithm[J]. Expert Systems with Applications, 2024, 247: 123306.
[17]
Zhou H, Zhang S, Peng J, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(12): 11106-11115.
[18]
Cui S, S, Ma Y, et al. Corrigendum to “improved informer PV power short-term prediction modelbased on weather typing and AHA-VMD-MPE”[J]. Energy, 2024, 310: 133290.
[19]
聂靖杰, 刘树鑫, 邢朝健, 等. 基于TPE-Informer模型的铁路继电器寿命预测[J]. 电气工程学报, 2024, 19(3): 98-106.
Nie Jingjie, Liu Shuxin, Xing Chaojian, et al. Life prediction of railroad relays based on TPE-Informer model[J]. Journal of Electrical Engineering, 2024, 19(3): 98-106.
[20]
覃文文, 彭栋梁, 戢晓峰, 等. 山区双车道公路借道超车轨迹预测模型[J]. 交通运输系统工程与信息, 1-13[2025-03-25]. http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html. http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html
Qin Wenwen, Peng Dongliang, Ji Xiaofeng, et al. Trajectory prediction model for borrowed overtaking on two-lane highways in mountainous areas[J]. Transportation Systems Engineering and Information, 1-13[2025-03-25].http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html. http://kns.cnki.net/kcms/detail/11.4520.U.20241025.1732.008.html
[21]
张兆宁, 查子奇. 基于多机场终端区交通态势的航班延误预测[J]. 科学技术与工程, 2024, 24(12): 5220-5226.
Zhang Zhaoning, Cha Ziqi. Flight delay prediction based on traffic dynamics in multi-airport terminalareas[J]. Science Technology and Engineering, 2024, 24(12): 5220-5226.
[22]
韩博, 林师卓, 王立婕. 机场能见度临近预测方法[J]. 安全与环境学报, 2024, 24(4): 1434-1441.
Han Bo, Lin Shizhuo, Wang Lijie. Near-term prediction method for airport visibility[J]. Journal of Safety and Environment, 2024, 24(4): 1434-1441.
2025年第25卷第19期
PDF下载
194
87
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405116
  • 接收时间:2024-07-08
  • 首发时间:2025-12-22
  • 出版时间:2025-07-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-08
  • 修回日期:2025-12-23
基金
国家自然科学基金民航联合基金重点项目(U2133207)
作者信息
    1 中国民航大学空中交通管理学院, 天津 300300
    2 中国民航大学交通科学与工程学院, 天津 30030
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405116
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