地学前缘 ›› 2025, Vol. 32 ›› Issue (4): 78-94.DOI: 10.13745/j.esf.sf.2025.4.62

• 智能矿产预测 • 上一篇    下一篇

基于多重分形与随机森林的新疆哈巴河金矿成矿预测

简富源1(), 张子鸣2, 董岳霖1, 张文璟2, 郝风云3, 王一鸣1, 王宇1, 张振杰1,*()   

  1. 1.中国地质大学(北京) 地球科学与资源学院, 地质过程与成矿预测全国重点实验室, 深时数字地球前沿科学中心, 北京 100083
    2.中国冶金地质总局西北局, 陕西 西安 710119
    3.哈巴河金坝矿业有限公司, 新疆 阿勒泰 836700
  • 收稿日期:2024-10-05 修回日期:2025-02-10 出版日期:2025-07-25 发布日期:2025-08-04
  • 通信作者: *张振杰(1988—),男,副教授,博士生导师,矿产普查与勘探专业,主要从事地学大数据和矿产智能预测研究。E-mail: zjzhang@cugb.edu.cn
  • 作者简介:简富源(2000—),男,博士研究生,地学大数据专业。E-mail: fyjian@email.cugb.edu.cn
  • 基金资助:
    国家重点研发计划项目(2023YFC2906402);国家自然科学基金项目(42430111);国家自然科学基金项目(42472358);国家自然科学基金项目(42050103);中央高校基本科研业务费项目(2652023001)

Multifractal analysis and random forest algorithm for mineral prospecting in the Habahe gold deposit, Xinjiang

JIAN Fuyuan1(), ZHANG Ziming2, DONG Yuelin1, ZHANG Wenjing2, HAO Fengyun3, WANG Yiming1, WANG Yu1, ZHANG Zhenjie1,*()   

  1. 1. School of Earth Sciences and Resources, State Key Laboratory of Geological Processes and Mineral Resources, Frontiers Science Center for Deep-time Digital Earth, China University of Geosciences (Beijing), Beijing 100083, China
    2. Northwest Bureau of China Metallurgical Geology Bureau, Xi’an 710119, China
    3. Habahe Jinba Mining Co.Ltd., Aertai 836700, China
  • Received:2024-10-05 Revised:2025-02-10 Online:2025-07-25 Published:2025-08-04

摘要:

大数据时代,基于机器学习的矿产智能预测方法得到了广泛的应用。基于分形与多重分形的非线性理论技术与矿产资源智能预测研究相结合,可以为矿产预测提供新思路与技术支撑。本文以新疆哈巴河金矿基地为研究对象,建立了以区域构造-矿化蚀变-磁异常-激电异常为基础的四要素信息找矿模型,实现了一种基于多重分形与随机森林算法的智能预测流程。运用S-A多重分形滤波技术和局部奇异性分析方法,分离区域物化数据变化背景与叠加异常,提取隐蔽的深部致矿弱信息;通过C-Nsum多重分形模型揭示钻孔Au指标含量隐藏的非线性特征,标定异常下限;使用随机森林与SHAP方法进行综合信息集成与特征贡献评价,实现了金矿产资源定量预测,圈定了3个成矿靶区且得到钻探验证,证明了多重分形理论在哈巴河金矿区矿产定量预测中的有效性,为后续的矿产勘查提供一定的依据。

关键词: S-A多重分形模型, 局部奇异性分析, 随机森林, 矿产预测, 机器学习, 哈巴河金矿

Abstract:

In the era of big data, machine learning-based intelligent mineral prediction methods have been widely applied. The integration of non-linear theory and techniques, such as fractal and multifractal approaches, into intelligent mineral prospecting research provides new perspectives and technical support. This study focuses on the Habahe gold deposit in Xinjiang, China, and establishes a four-factor information prospecting model based on regional structure, mineralization alteration, magnetic anomalies, and induced polarization anomalies. An intelligent prediction workflow is implemented, by combining the multifractal method with the random forest algorithm. The S-A multifractal filtering technique and local singularity analysis are employed to separate the background variations of regional geophysical and geochemical data from superimposed anomalies, enabling the extraction of concealed information indicative of deep mineralization. The C-Nsum multifractal model is applied to reveal the hidden nonlinear characteristics of gold content in drilling data and determine anomaly thresholds. Subsequently, the random forest algorithm and SHAP method is utilized for comprehensive information integration and feature contribution evaluation, achieving quantitative prediction of gold mineral resources. This approach delineated three prospective mineralization targets, which were validated through drilling, demonstrating the effectiveness of multifractal theory in quantitative mineral prediction within the Habahe gold deposit area. The results provide a robust basis for subsequent mineral exploration efforts.

Key words: S-A multifractal model, local singularity analysis, random forest, mineral prospectivity, machine learning, Habahe gold deposit

中图分类号: