Next Article in Journal
Effect of Acidified Water Glass on Flotation Separation of Fluorite and Calcite
Previous Article in Journal
Reductant-Free Cobalt Recovery from Similar Copper–Cobalt Oxide Ores via Synergistic Reductive-Acid Leaching
Previous Article in Special Issue
Inversion of Vertical Electrical Sounding Data Based on PSO-BP Neural Network
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Minerals
Volume 15
Issue 10
10.3390/min15101023
minerals-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Enhancing Geological Knowledge Engineering with Retrieval-Augmented Generation: A Case Study of the Qin–Hang Metallogenic Belt

by
Jianhua Ma
1,2,3,
Yongzhang Zhou
1,2,3,*,
Luhao He
1,2,3,4,*,
Qianlong Zhang
1,2,3,
Muhammad Atif Bilal
5 and
Yuqing Zhang
1,2,3
1
Center for Earth Environment and Earth Resources, Sun Yat-sen University, Zhuhai 519000, China
2
School of Earth Sciences and Engineering, Sun Yat-sen University, Zhuhai 519000, China
3
Key Laboratory of Geological Processes and Mineral Resources Exploration, Zhuhai 519000, China
4
School of Environmental Sciences and Engineering, Sun Yat-sen University, Guangzhou 510000, China
5
College of Geoexploration Science & Technology, Jilin University, Changchun 130061, China
*
Authors to whom correspondence should be addressed.
Minerals 2025, 15(10), 1023; https://doi.org/10.3390/min15101023
Submission received: 30 July 2025 / Revised: 16 September 2025 / Accepted: 22 September 2025 / Published: 26 September 2025
(This article belongs to the Special Issue Application of Big Data Mining, Machine Learning and Artificial Intelligence in Geoscience, 2nd Edition)
Versions Notes

Abstract

This study presents a domain-adapted retrieval-augmented generation (RAG) pipeline that integrates geological knowledge with large language models (LLMs) to support intelligent question answering in the metallogenic domain. Focusing on the Qin–Hang metallogenic belt in South China, we construct a bilingual question-answering (QA) corpus derived from 615 authoritative geological publications, covering topics such as regional tectonics, ore-forming processes, structural evolution, and mineral resources. Using the ChatGLM3-6B language model and LangChain framework, we embed the corpus into a semantic vector database via Sentence-BERT and FAISS, enabling dynamic retrieval and grounded response generation. The RAG-enhanced model significantly outperforms baseline LLMs—including ChatGPT-4, Bing, and Gemini—in a comparative evaluation using BLEU, precision, recall, and F1 metrics, achieving an F1 score of 0.8689. The approach demonstrates high domain adaptability and reproducibility. All datasets and codes are openly released to facilitate application in other metallogenic belts. This work illustrates the potential of LLM-based knowledge engineering to support digital geoscientific research and smart mining.
Keywords: large language models; retrieval-augmented generation; geological knowledge base; Qin–Hang metallogenic belt; geoinformatics; semantic search; metallogenic systems large language models; retrieval-augmented generation; geological knowledge base; Qin–Hang metallogenic belt; geoinformatics; semantic search; metallogenic systems

Share and Cite

MDPI and ACS Style

Ma, J.; Zhou, Y.; He, L.; Zhang, Q.; Bilal, M.A.; Zhang, Y. Enhancing Geological Knowledge Engineering with Retrieval-Augmented Generation: A Case Study of the Qin–Hang Metallogenic Belt. Minerals 2025, 15, 1023. https://doi.org/10.3390/min15101023

AMA Style

Ma J, Zhou Y, He L, Zhang Q, Bilal MA, Zhang Y. Enhancing Geological Knowledge Engineering with Retrieval-Augmented Generation: A Case Study of the Qin–Hang Metallogenic Belt. Minerals. 2025; 15(10):1023. https://doi.org/10.3390/min15101023

Chicago/Turabian Style

Ma, Jianhua, Yongzhang Zhou, Luhao He, Qianlong Zhang, Muhammad Atif Bilal, and Yuqing Zhang. 2025. "Enhancing Geological Knowledge Engineering with Retrieval-Augmented Generation: A Case Study of the Qin–Hang Metallogenic Belt" Minerals 15, no. 10: 1023. https://doi.org/10.3390/min15101023

APA Style

Ma, J., Zhou, Y., He, L., Zhang, Q., Bilal, M. A., & Zhang, Y. (2025). Enhancing Geological Knowledge Engineering with Retrieval-Augmented Generation: A Case Study of the Qin–Hang Metallogenic Belt. Minerals, 15(10), 1023. https://doi.org/10.3390/min15101023

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop