Academic Journal
Προβολή σε EDS

A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models.
Συγγραφείς: Li, Hao, Yue, Peng, Wu, Haoru, Teng, Baoxin, Zhao, Yongkun, Liu, Changfeng
Πηγή: International Journal of Digital Earth; Dec2025, Vol. 18 Issue 1, p1-24, 24p
Θεματικοί όροι: Geospatial data, Knowledge graphs, Spatiotemporal processes, Data mining, Information retrieval, Natural language processing, Language models
Περίληψη: The rapid advancement of Earth observation technologies has resulted in an explosive growth of geoscientific data. Efficient retrieval of such data is essential but often challenging, especially for non-experts, due to decentralized data sources and limited semantic support in existing portals. To address these challenges, we propose the Geospatial Data service-oriented Question-Answering (GDQA) system, which combines a geospatial data knowledge graph (GDKG) with large language models (LLMs) to enable natural language-based data discovery. Our framework includes two key components. First, we construct the GDKG by aggregating data from five major portals and employing an information extraction model to automatically identify and structure fine-grained knowledge from unstructured texts. Second, we develop a method called Spatio-Temporal Reasoning on Knowledge Graphs (STRKG), which enables LLMs to perform reasoning and exploration over GDKG, enhancing their ability to understand and respond to complex geoscientific queries. While LLMs contribute to flexible natural language interaction, the GDKG complements them with domain-specific knowledge. To evaluate our system, we design a set of competency questions spanning four dimensions: constraint quantity, reasoning depth, spatiotemporal logic, and inference complexity. Compared to baseline approaches including KGQArr, Text2Cypher, KAPING, and ToG, our method achieves superior performance in both accuracy and efficiency, significantly reducing time and token costs. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Digital Earth is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Βάση Δεδομένων: Complementary Index
FullText Text:
  Availability: 0
Header DbId: edb
DbLabel: Complementary Index
An: 187565375
RelevancyScore: 1041
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1040.81262207031
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Li%2C+Hao%22">Li, Hao</searchLink><br /><searchLink fieldCode="AR" term="%22Yue%2C+Peng%22">Yue, Peng</searchLink><br /><searchLink fieldCode="AR" term="%22Wu%2C+Haoru%22">Wu, Haoru</searchLink><br /><searchLink fieldCode="AR" term="%22Teng%2C+Baoxin%22">Teng, Baoxin</searchLink><br /><searchLink fieldCode="AR" term="%22Zhao%2C+Yongkun%22">Zhao, Yongkun</searchLink><br /><searchLink fieldCode="AR" term="%22Liu%2C+Changfeng%22">Liu, Changfeng</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: International Journal of Digital Earth; Dec2025, Vol. 18 Issue 1, p1-24, 24p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Geospatial+data%22">Geospatial data</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+graphs%22">Knowledge graphs</searchLink><br /><searchLink fieldCode="DE" term="%22Spatiotemporal+processes%22">Spatiotemporal processes</searchLink><br /><searchLink fieldCode="DE" term="%22Data+mining%22">Data mining</searchLink><br /><searchLink fieldCode="DE" term="%22Information+retrieval%22">Information retrieval</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The rapid advancement of Earth observation technologies has resulted in an explosive growth of geoscientific data. Efficient retrieval of such data is essential but often challenging, especially for non-experts, due to decentralized data sources and limited semantic support in existing portals. To address these challenges, we propose the Geospatial Data service-oriented Question-Answering (GDQA) system, which combines a geospatial data knowledge graph (GDKG) with large language models (LLMs) to enable natural language-based data discovery. Our framework includes two key components. First, we construct the GDKG by aggregating data from five major portals and employing an information extraction model to automatically identify and structure fine-grained knowledge from unstructured texts. Second, we develop a method called Spatio-Temporal Reasoning on Knowledge Graphs (STRKG), which enables LLMs to perform reasoning and exploration over GDKG, enhancing their ability to understand and respond to complex geoscientific queries. While LLMs contribute to flexible natural language interaction, the GDKG complements them with domain-specific knowledge. To evaluate our system, we design a set of competency questions spanning four dimensions: constraint quantity, reasoning depth, spatiotemporal logic, and inference complexity. Compared to baseline approaches including KGQArr, Text2Cypher, KAPING, and ToG, our method achieves superior performance in both accuracy and efficiency, significantly reducing time and token costs. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Digital Earth is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=187565375
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/17538947.2025.2510566
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 1
    Subjects:
      – SubjectFull: Geospatial data
        Type: general
      – SubjectFull: Knowledge graphs
        Type: general
      – SubjectFull: Spatiotemporal processes
        Type: general
      – SubjectFull: Data mining
        Type: general
      – SubjectFull: Information retrieval
        Type: general
      – SubjectFull: Natural language processing
        Type: general
      – SubjectFull: Language models
        Type: general
    Titles:
      – TitleFull: A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Li, Hao
      – PersonEntity:
          Name:
            NameFull: Yue, Peng
      – PersonEntity:
          Name:
            NameFull: Wu, Haoru
      – PersonEntity:
          Name:
            NameFull: Teng, Baoxin
      – PersonEntity:
          Name:
            NameFull: Zhao, Yongkun
      – PersonEntity:
          Name:
            NameFull: Liu, Changfeng
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 17538947
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: International Journal of Digital Earth
              Type: main
ResultId 1