EKUM: An Accurate Method for Updating Knowledge Graphs in Earth System Science for Novel Thematic Terms
文献类型：期刊论文
| 作者 | Chen, Jin1,4; Wang, Shu1,2,3; Zhu, Yunqiang1,2,3; Duan, Fuzhou4; Dai, Xiaoliang1,3 |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2025 |
| 卷号 | 63页码:3001812 |
| 关键词 | Earth Knowledge graphs Semantics Accuracy Reliability Vectors Logic gates Terrestrial atmosphere Natural resources Laboratories Dynamic updating Earth system science hierarchical relationship matching knowledge graph thematic terms |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2025.3624018 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Efficient maintenance of the Earth system science knowledge graph (ESSKG) is essential for structuring and evolving scientific knowledge in the context of AI-driven research. However, the rapid emergence of new terminology and reliance on manual curation constrain the timeliness and scalability of updates. A multidimensional feature deep alignment mechanism (MFDA) and an end-to-end update workflow (EKUM) are introduced to address this challenge. MFDA integrates structural, relational, and contextual features through two-stage fusion with cross feature gating, dynamic temperature contrastive alignment, and a sparsified high order neighborhood module. EKUM operationalizes MFDA in a pipeline for corpus preparation, term recognition, alignment, and graph update. Experiments show that MFDA surpasses character based, representation learning, and large language model (LLM) enhanced baselines, achieving precision 0.943 and right to left mean reciprocal rank (MRR) 0.677, exceeding the best-performing baseline by over 11%. Deployed within EKUM, 2889 new terms from 1478 peer-reviewed articles (2012-2024) are integrated, expanding the ESSKG to 6352 entities and 10 747 relations with refined hierarchies and cross layer links. Longitudinal evaluation from 2013 to 2022 indicates stable precision and slower error growth than baselines, mitigating cascading errors. Layer and regional growth patterns reflect differences in data coverage, observing infrastructure, terminology maturity, and cataloging practices, underscoring a scalable, timely, and interpretable pathway for ESSKG evolution. |
| URL标识 | 查看原文 |
| WOS关键词 | PROGRESS |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001626459000043 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/219530]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Wang, Shu |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China; 2.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing 210023, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China; 4.Capital Normal Univ, Coll Resources Environm & Tourism, Beijing 100048, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Chen, Jin,Wang, Shu,Zhu, Yunqiang,et al. EKUM: An Accurate Method for Updating Knowledge Graphs in Earth System Science for Novel Thematic Terms[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:3001812. |
| APA | Chen, Jin,Wang, Shu,Zhu, Yunqiang,Duan, Fuzhou,&Dai, Xiaoliang.(2025).EKUM: An Accurate Method for Updating Knowledge Graphs in Earth System Science for Novel Thematic Terms.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,3001812. |
| MLA | Chen, Jin,et al."EKUM: An Accurate Method for Updating Knowledge Graphs in Earth System Science for Novel Thematic Terms".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):3001812. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。