多模态遥感基础大模型:研究现状与未来展望

P237; 遥感对地观测能力的稳步提升为遥感基础大模型的涌现和发展奠定了数据基础.针对不同数据及任务类型,设计不同的深度网络骨架及优化方法必将浪费大量人力物力.为了解决上述问题,国内外研究学者转入遥感基础大模型研究,并提出了大量优秀统一模型.为提高遥感基础大模型的泛化性和可解释性,引入泛在的地学知识被认为是一项关键技术.目前,已有相关工作在遥感基础大模型的结构设计或预训练方法中挖掘或整合了地学知识,但尚无文献系统性阐述和总结地学知识引导的遥感基础大模型的研究现状.因此,本文首先对大规模遥感基础模型预训练数据集进行了归纳和总结,并分类回顾了遥感基础大模型的研究进展;然后,介绍了地学知识引导的遥感...

Full description

Saved in:
Bibliographic Details
Published in测绘学报 Vol. 53; no. 10; pp. 1942 - 1954
Main Authors 张永军, 李彦胜, 党博, 武康, 郭昕, 王剑, 陈景东, 杨铭
Format Journal Article
LanguageChinese
Published 武汉大学遥感信息工程学院,湖北武汉 430079%蚂蚁集团,浙江 杭州 310013 26.11.2024
Subjects
预训练数据集
遥感智能解译
geographic knowledge
remote sensing foundation models
遥感基础大模型
pre-training dataset
地学知识
remote sensing intelligent interpretation
Online AccessGet full text

Cover

Abstract P237; 遥感对地观测能力的稳步提升为遥感基础大模型的涌现和发展奠定了数据基础.针对不同数据及任务类型,设计不同的深度网络骨架及优化方法必将浪费大量人力物力.为了解决上述问题,国内外研究学者转入遥感基础大模型研究,并提出了大量优秀统一模型.为提高遥感基础大模型的泛化性和可解释性,引入泛在的地学知识被认为是一项关键技术.目前,已有相关工作在遥感基础大模型的结构设计或预训练方法中挖掘或整合了地学知识,但尚无文献系统性阐述和总结地学知识引导的遥感基础大模型的研究现状.因此,本文首先对大规模遥感基础模型预训练数据集进行了归纳和总结,并分类回顾了遥感基础大模型的研究进展;然后,介绍了地学知识引导的遥感影像智能解译算法以及面向遥感基础大模型的地学知识挖掘与利用进展;最后,针对该领域仍然面临的挑战提出了几点未来研究展望,旨在为遥感基础大模型的未来研究提供探索方向参考.
AbstractList P237; 遥感对地观测能力的稳步提升为遥感基础大模型的涌现和发展奠定了数据基础.针对不同数据及任务类型,设计不同的深度网络骨架及优化方法必将浪费大量人力物力.为了解决上述问题,国内外研究学者转入遥感基础大模型研究,并提出了大量优秀统一模型.为提高遥感基础大模型的泛化性和可解释性,引入泛在的地学知识被认为是一项关键技术.目前,已有相关工作在遥感基础大模型的结构设计或预训练方法中挖掘或整合了地学知识,但尚无文献系统性阐述和总结地学知识引导的遥感基础大模型的研究现状.因此,本文首先对大规模遥感基础模型预训练数据集进行了归纳和总结,并分类回顾了遥感基础大模型的研究进展;然后,介绍了地学知识引导的遥感影像智能解译算法以及面向遥感基础大模型的地学知识挖掘与利用进展;最后,针对该领域仍然面临的挑战提出了几点未来研究展望,旨在为遥感基础大模型的未来研究提供探索方向参考.
Abstract_FL The increasing remote sensing capabilities for Earth observation have eased the access to abundant data and enabled the emergence and development of remote sensing foundation models(RSFMs).Designing distinct deep neural networks and optimizing for different data and task types require substantial development efforts and prohibitively high computational re-sources.In order to address these issues,researchers in the remote sensing field have shifted their focus to the study of RSFMs and presented many dedicated designed unified models.To enhance the generalizability and interpretability of RSFMs,the inte-gration of extensive geographic knowledge has been recognized as a pivotal/key approach.While existing works have explored or incorporated geographic knowledge into the architecture design or pre-training methods of RSFMs,there lacks of a compre-hensive survey to review the current status of geographic knowledge-guided RSFMs.Therefore,this paper starts with summa-rizing and categorizing large-scale pre-training datasets and then provides an overview of the research progress in this field.Subsequently,we introduce intelligent interpretation algorithms for remote sensing imagery guided by geographic knowledge,along with advancements in the exploration and utilization of geographic knowledge specifically tailored for RSFMs.Finally,several future research prospects are outlined to tackle the persisting challenges in this field,aiming to shed light on future in-vestigations into RSFMs.
Author 张永军
陈景东
王剑
杨铭
郭昕
党博
李彦胜
武康
AuthorAffiliation 武汉大学遥感信息工程学院,湖北武汉 430079%蚂蚁集团,浙江 杭州 310013
AuthorAffiliation_xml – name: 武汉大学遥感信息工程学院,湖北武汉 430079%蚂蚁集团,浙江 杭州 310013
Author_FL WU Kang
GUO Xin
LI Yansheng
CHEN Jing-dong
YANG Ming
DANG Bo
WANG Jian
ZHANG Yongjun
Author_FL_xml – sequence: 1
  fullname: ZHANG Yongjun
– sequence: 2
  fullname: LI Yansheng
– sequence: 3
  fullname: DANG Bo
– sequence: 4
  fullname: WU Kang
– sequence: 5
  fullname: GUO Xin
– sequence: 6
  fullname: WANG Jian
– sequence: 7
  fullname: CHEN Jing-dong
– sequence: 8
  fullname: YANG Ming
Author_xml – sequence: 1
  fullname: 张永军
– sequence: 2
  fullname: 李彦胜
– sequence: 3
  fullname: 党博
– sequence: 4
  fullname: 武康
– sequence: 5
  fullname: 郭昕
– sequence: 6
  fullname: 王剑
– sequence: 7
  fullname: 陈景东
– sequence: 8
  fullname: 杨铭
BookMark eNrjYmDJy89LZWCQNTTQMzS0NDHXz9JzdHcO1jMyMDIBEwYGhpYsDJyGQFrX0NTSlIOBt7g4M8nAwNTE2NzU2JKTwerpklnPVix81tD4snHps5b5T-fver6w4emS5UDBp_O6rZ4vmPJ85bbnfRued217sqPv2ZxVz-Yufbpx6rM5s3kYWNMSc4pTeaE0N0Oom2uIs4euj7-7p7Ojj24x0F5LXePUJCPjJCNDMwsDiyQDSzPDJFOjVIO0NKMUcyMLgzQz05RUC8O0xJTEpBSgmIFFolmSsYlRSoplWrK5sXmqpTE3gyrE3PLEvLTEvPT4rPzSojygjfHJGRVJIG8C7TGwNAYAOqZe3w
ClassificationCodes P237
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.11947/j.AGCS.2024.20240019
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Astronomy & Astrophysics
DocumentTitle_FL Multi-modal remote sensing large foundation models:current research status and future prospect
EndPage 1954
ExternalDocumentID chxb202410009
GroupedDBID -01
2B.
4A8
5VS
5XA
5XB
7X2
92E
92I
93N
ABJNI
ACGFS
AEUYN
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ATCPS
BBNVY
BENPR
BHPHI
BKSAR
CCEZO
CCPQU
CCVFK
CW9
HCIFZ
IPNFZ
M0K
M7P
OK1
P2P
PATMY
PCBAR
PHGZM
PHGZT
PIMPY
PMFND
PSX
PYCSY
RIG
TCJ
TGP
U1G
U5K
ID FETCH-LOGICAL-s1009-3eb23b216808b0961b52e0ff2d7280f65de81fadabdf2d08a6b342dd9fc737e93
ISSN 1001-1595
IngestDate Thu May 29 04:11:08 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 10
Keywords 预训练数据集
遥感智能解译
geographic knowledge
remote sensing foundation models
遥感基础大模型
pre-training dataset
地学知识
remote sensing intelligent interpretation
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1009-3eb23b216808b0961b52e0ff2d7280f65de81fadabdf2d08a6b342dd9fc737e93
PageCount 13
ParticipantIDs wanfang_journals_chxb202410009
PublicationCentury 2000
PublicationDate 2024-11-26
PublicationDateYYYYMMDD 2024-11-26
PublicationDate_xml – month: 11
  year: 2024
  text: 2024-11-26
  day: 26
PublicationDecade 2020
PublicationTitle 测绘学报
PublicationTitle_FL Acta Geodaetica et Cartographica Sinica
PublicationYear 2024
Publisher 武汉大学遥感信息工程学院,湖北武汉 430079%蚂蚁集团,浙江 杭州 310013
Publisher_xml – name: 武汉大学遥感信息工程学院,湖北武汉 430079%蚂蚁集团,浙江 杭州 310013
SSID ssib005437539
ssib038074662
ssib051373695
ssib002263888
ssib000862384
ssj0058465
Score 2.439258
Snippet P237;...
SourceID wanfang
SourceType Aggregation Database
StartPage 1942
Title 多模态遥感基础大模型:研究现状与未来展望
URI https://d.wanfangdata.com.cn/periodical/chxb202410009
Volume 53
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LbhMx0GrLhQviqfKqcsBcqpR92Wv3ZqcbKhBIiFbqrVpnd-mFVCKpBD21EieQeoILFEqlVjxOcKkQX8FHkET8BTPeTWrUSjwu1mR2PDOeWccz6xch12LIOXgKkVvqpUU9ErJVN1ym9TgI_MKIKPNy3Dt85y6fX4xuLbGlsfHvzqqlta6Zaa0fu6_kf7wKOPAr7pL9B8-OmAICYPAvlOBhKP_KxzRhVEVUKppwqgRVPgLCg_CQJhJLxSwGaJpIDKUG4hgpgaysrmKnOtAkVGjQwJJ5VEYWkFRzBERCtWcBZTER1QKRwEE2qLKayDkrl1HtU8mqR1K7cTAiNUNBwEprKoVVBipyq7ACDsN3wXJqoC5YyUOBgBF8yNKSWKmoB9CWXECtEAS7XASztgJgDgC3ciWZoXl07H4KCSLcE1jut7cvr0POsYVCOnYcteGo9cFSzaGH4JH1h44tTYzWR1s41aWkKoAOYKXAT6udADvGRxWYjkIIwiQNGDYbmiiCIWBfBKnRXOhb7TBlKKNkIZvTQ8fNVXrJZBpnZcotvNWwhQvjIDBl7rjGQrf_es4o5cvyRLMq4sFD_44fTWUU2-FU3Wzcn0GL2wLTgsPwYbSos7Xy2OBjnDGS4-REAIkb3ily-54b8EO4LdyAEv7_nQPzWBRC_jwKsPE2hIgfHmjJ_DAOuRwluBg9M7ueoWp_tUcPFb9xnNp2a167SNsPnChy4TQ5VaV_NVX25TNkbH3lLJlUHZyQWn34pHa9ZuHye2PnHJnt7b3qf9jtb2z-3NzvP93p7Xwb7G709t4Dsvf2-ezg3YvBx4PB1ufBs4MfX7f625_6b_Z7X172t1-fJ4vNZKExX6-uO6l3fJyiDHMThCbw8TIcgzcxGRbkXlEEGV4hV3CW5cIv0iw1GeA8kXITRkGWyaIVh3Euwwtkor3azidJzUBtyJuyHD-Y-H5qTAtC9YLHMJoHkANeJFOVGZarv7PO8m_uu_Qngsvk5GEPvEImuo_W8qsQnnfNlPX4L-5EpKA
linkProvider Colorado Alliance of Research Libraries
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%A4%9A%E6%A8%A1%E6%80%81%E9%81%A5%E6%84%9F%E5%9F%BA%E7%A1%80%E5%A4%A7%E6%A8%A1%E5%9E%8B%3A%E7%A0%94%E7%A9%B6%E7%8E%B0%E7%8A%B6%E4%B8%8E%E6%9C%AA%E6%9D%A5%E5%B1%95%E6%9C%9B&rft.jtitle=%E6%B5%8B%E7%BB%98%E5%AD%A6%E6%8A%A5&rft.au=%E5%BC%A0%E6%B0%B8%E5%86%9B&rft.au=%E6%9D%8E%E5%BD%A6%E8%83%9C&rft.au=%E5%85%9A%E5%8D%9A&rft.au=%E6%AD%A6%E5%BA%B7&rft.date=2024-11-26&rft.pub=%E6%AD%A6%E6%B1%89%E5%A4%A7%E5%AD%A6%E9%81%A5%E6%84%9F%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E6%B9%96%E5%8C%97%E6%AD%A6%E6%B1%89+430079%25%E8%9A%82%E8%9A%81%E9%9B%86%E5%9B%A2%2C%E6%B5%99%E6%B1%9F+%E6%9D%AD%E5%B7%9E+310013&rft.issn=1001-1595&rft.volume=53&rft.issue=10&rft.spage=1942&rft.epage=1954&rft_id=info:doi/10.11947%2Fj.AGCS.2024.20240019&rft.externalDocID=chxb202410009
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fchxb%2Fchxb.jpg