地学前缘 ›› 2026, Vol. 33 ›› Issue (4): 327-339.DOI: 10.13745/j.esf.sf.2026.2.26

• 矿产资源评价预测 • 上一篇    下一篇

面向矿产资源评价预测的生成式先验转换模型(MineralGPT):以崤山-熊耳山地区金多金属矿找矿靶区优选为例

邓吉秋1,2(), 郭志勇1,2,*(), 刘文毅3,4, 张超林1,2, 王琦琦3,4   

  1. 1.中南大学 地球科学与信息物理学院, 湖南 长沙 410083
    2.中南大学 有色金属成矿预测与地质环境监测教育部重点实验室, 湖南 长沙 410083
    3.河南省地质研究院, 河南 郑州 450016
    4.高分辨率对地观测系统河南数据与应用中心地质分中心, 河南 郑州 450016
  • 收稿日期:2025-12-10 修回日期:2026-02-09 出版日期:2026-07-25 发布日期:2026-04-20
  • 通信作者: 郭志勇(1997—),男,博士研究生,地质资源与地质工程专业。E-mail: zhiyongguo1015@163.com
  • 作者简介:邓吉秋(1972—),男,博士,副教授,博士生导师,主要从事地学大数据与人工智能、地学三维建模与可视化等研究。E-mail:gis00@163.com
  • 基金资助:
    国家自然科学基金项目(42172330);2018年度河南省国土资源科研项目([2018]98-17);2021年度河南省自然资源科研项目([2021]157-12);高分辨率对地观测系统国家科技重大专项(80-Y50G19-9001-22/23)

Generative Prior Transformation Model for mineral resources evaluation and prediction (MineralGPT): A case study of prospective target area selection for the Xiaoshan-Xiong’ershan area gold polymetallic deposit

DENG Jiqiu1,2(), GUO Zhiyong1,2,*(), LIU Wenyi3,4, ZHANG Chaolin1,2, WANG Qiqi3,4   

  1. 1. School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
    2. Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring of Ministry of Education, Central South University, Changsha 410083, China
    3. Henan Academy of Geology, Zhengzhou 450016, China
    4. The Geological Sub Center of Henan Data and Application Center of Earth Observation System with High Resolution, Zhengzhou 450016, China
  • Received:2025-12-10 Revised:2026-02-09 Online:2026-07-25 Published:2026-04-20

摘要:

矿产资源是经济社会发展的重要物质基础。开展矿产资源评价与预测,能为矿产资源的勘查、开发与保护提供科学依据。然而,基于传统人工分析的找矿方法存在主观性强、具有局限性且成本高等问题,而基于计算机的综合评价方法则常面临数据利用不充分、模型固定及文本资料利用率低等挑战。为此,本研究将专家知识与人工分析经验转化为先验规则,以文本分析为基础,引入自然语言处理方法并结合计算机技术,提出了一种新的矿产资源评价预测模型——生成式先验转换模型(MineralGPT)。该模型框架以先验知识的描述、存储、解析为核心驱动,支撑包括数据处理与分析、成矿信息提取与找矿预测、内容生成与优化在内的多类型算法任务。以崤山-熊耳山地区金多金属矿找矿靶区优选为例,在MineralGPT框架下构建基于词项加权的矿集区找矿靶区优选模型。实验结果表明:在少量数据支持下,MineralGPT的预测结果几乎与专家评价一致。相较于ChatGPT等依赖庞大数据与算力的大型语言模型,MineralGPT具有低成本、受限少、可定制性高等优势。通过将先验知识进行规则化描述、存储与解析,MineralGPT不仅为矿产资源评价提供了新方法,亦为融合规则与学习的新一代人工智能技术发展提供了新思路。

关键词: 矿产资源评价预测, 生成式先验转换模型, 词项权重计算, 词项关联分析, 找矿靶区优选

Abstract:

Mineral resources constitute a critical material foundation for socioeconomic development. Their assessment and prospectivity modeling provide a scientific basis for sustainable resource management. Traditional evaluation methods are often costly, time-consuming, and constrained by limited data-processing capabilities. Conversely, computational approaches frequently rely on fixed patterns and cannot adequately incorporate expert knowledge. Moreover, the utilization of multi-source heterogeneous data, particularly unstructured text data, remains low. To address these limitations, this study formalizes expert knowledge and analytical methods into prior rules and proposes a novel framework: the Mineral Generative Prior Transformation Model (MineralGPT). The MineralGPT framework is driven by the rule-based description, storage, and analysis of prior knowledge, supporting diverse tasks such as data processing, metallogenic information extraction, prospectivity modeling, and content optimization. A case study optimizing gold-polymetallic exploration targets in the Xiaoshan-Xiongershan area demonstrates the model's efficacy. Experiments on a term-weighting-based target optimization model within MineralGPT show that results, even when supported by limited data, achieve high consistency with expert evaluations. Compared to large language models (LLMs) like ChatGPT, which require massive data and computing power, MineralGPT offers advantages including lower cost, fewer constraints, and high customizability.By integrating rule-based prior knowledge, MineralGPT provides a novel methodology for mineral resource assessment and prediction. Furthermore, it offers a new perspective for developing next-generation artificial intelligence that synergistically combines rule-based and learning-based paradigms.

Key words: mineral resources evaluation and prediction, Generative Prior Transformation Model, calculation of term weighting, term association analysis, prospecting target area optimization

中图分类号: