Jiyin Zhang, Weilin Chen, Chenhao Li, Xiaogang Ma
Knowledge extraction from unstructured Earth Science documents into standardized knowledge bases is a complex task that used to be heavily reliant on manual curation and domain expertise. As an effort to automate this process, we proposed a modularized multi-agent system framework, Adaptive Geo Knowledge Extraction (AGeoKE), that leverages Large Language Models (LLMs) to automatically extract and standardize knowledge from a specific geological document while maintaining the flexibility to adapt to different controlled vocabularies with minimum human intervention. The framework employs a Model Context Protocol (MCP) architecture with four modularized agent teams performing a streamlined workflow from raw PDF Optical Character Recognition (OCR) preprocessing to final well-structured knowledge output with controlled vocabulary alignment. To address concerns about the quality of AI-generated content, the framework utilizes a series of quality control mechanisms, including multi-version reviewing, error reflection, and term matching validation, to ensure the reliability of the extracted knowledge and the robustness of the automated process. The proposed method features a vocabulary-adaptive design that allows the framework to adapt to different controlled vocabularies without extensive reconfiguration, to facilitate the generalizability of the framework. A case study on the Mineral Deposit Models datasets demonstrates the effectiveness of the proposed method, highlighting the significant improvements of the implemented quality control mechanisms. By combining automated workflow design, simplified vocabulary alignment, and comprehensive quality validation, AGeoKE provides a scalable and adaptive foundation of knowledge extraction across Earth Science domains and beyond, enabling efficient transformation of legacy scientific documents into structured, machine-readable knowledge bases.