209 Deep-Time Earth and the AI Revolution

We invite overviews related to compiling and deciphering large regional to global-scale datasets on the fascinating history of our Earth and Solar System, and to unraveling the interplay of processes that shaped the past.

Tuesday, 21 October 2025
1:30 PM - 5:30 PM
HBGCC, 301C

Ontology-Guided Construction of Geoscience Knowledge Graphs Using Large Language Models

Paper number: 209-9
Program: Technical Sessions
Time: 3:45 PM – 4:00 PM

Authors

  • Ting Yu
    Zhejiang Lab, Hangzhou City, Zhejiang Province
  • Zhiqiang Feng
    Zhejiang Center for Deep-time Digital Earth, Hangzhou City, Zhejiang Province
  • Xianming Tang
    Petroleum Exploration and Production Research Institute, SINOPEC, Beijing
  • Ting Jiang
    Zhejiang Lab, Hangzhou City, Zhejiang Province
  • Wenxun Wu
    Zhejiang Lab, Hangzhou City, Zhejiang Province
  • Jaward MOHAMED
    Zhejiang Lab, Hangzhou City, Zhejiang Province
  • Hongyang Chen
    Zhejiang Lab, Hangzhou City, Zhejiang Province
  • Jieping Ye
    Zhejiang Lab, Hangzhou, Zhejiang Province
  • Grant Boquet Presenting Author
    GeoGPT, Zhejiang Lab
  • Huiting Hu
    Northeast Petroleum University, Daqing, Heilongjiang Province
  • Yilin Li
    Northeast Petroleum University, Daqing, Heilongjiang Province

Abstract

Knowledge graphs serve as foundational semantic infrastructures for integrating heterogeneous geoscience data—such as geological, mineral, and environmental information—and are essential for knowledge-driven intelligent analysis and decision support. However, traditional knowledge graph construction faces challenges in extraction automation, semantic consistency, and ontology alignment. To address these issues, this paper proposes a method for constructing geoscience knowledge graphs by combining large language models (LLMs) with ontological constraints, enabling high-precision, structurally sound, and semantically interpretable automated knowledge extraction.

The method employs predefined geoscience ontologies as structural and semantic frameworks, embedding their classes, attributes, relational hierarchies, and logical rules into LLM prompt designs to guide knowledge extraction. Structured prompts enable LLMs to identify ontology-compliant entities and relationships from unstructured texts—including research literature, technical reports, and field records—effectively reducing hallucinations and improving semantic accuracy. An iterative verification mechanism compares initial extractions with the ontology via logical reasoning to detect and correct invalid triples. Few-shot learning and chain-of-thought prompting further enhance model performance in low-resource settings, while rule-based validation ensures consistency and reduces noise.

Evaluations on real-world geoscience text datasets show that, compared to non-ontology-guided baselines, the proposed approach improves relationship extraction accuracy by 22.6% and achieves an F1 score of 84.3%. The resulting knowledge graph demonstrates superior interpretability and ontological coherence. This study presents semantic guidance and generative intelligence paradigm for high-quality domain-specific knowledge graph construction, advancing geoscience knowledge management toward automation, standardization, and intelligence.

Geological Society of America Abstracts with Programs. Vol. 57, No. 6

doi: 10.1130/abs/2025AM-414814

© Copyright 2025 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.