EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Hao Li, Peng Yue, Haoru Wu, Baoxin Teng, Yongkun Zhao, Changfeng Liu

International Journal of Digital Earth · 25.08.2025 · 18 (1)

DOI: 10.1080/17538947.2025.2510566 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Digital Earth, online erschienen am 26.05.2025. Verfasst von Hao Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Chongqing Technology Innovation and Application Development Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Natural Science Foundation of China
  • Chongqing Technology Innovation and Application Development Project

Zitieren

APA

Li, H., Yue, P., Wu, H., Teng, B., Zhao, Y., & Liu, C. (2025). A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models. International Journal of Digital Earth, 18(1). https://doi.org/10.1080/17538947.2025.2510566

Vancouver

Li H, Yue P, Wu H, Teng B, Zhao Y, Liu C. A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models. International Journal of Digital Earth. 2025;18(1). doi:10.1080/17538947.2025.2510566

BibTeX
@article{Li2025,
  author = {Li, Hao and Yue, Peng and Wu, Haoru and Teng, Baoxin and Zhao, Yongkun and Liu, Changfeng},
  title = {A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models},
  journal = {International Journal of Digital Earth},
  year = {2025},
  volume = {18},
  number = {1},
  doi = {10.1080/17538947.2025.2510566}
}
Kostenlos starten →