摘要
随着人工智能和大数据技术的迅速发展,基于机器学习的矿产资源智能预测已成为当前研究热点。然而,部分机器学习模型嵌套的复杂非线性网络结构和抽象表达,具有高度不透明的黑盒属性,导致智能预测结果与成矿作用之间缺乏相关解释,降低了预测模型的泛化能力和预测结果的可靠程度。为解决以上问题,本研究提出了知识-数据联合驱动的可解释矿产资源智能预测方法。首先,采用最佳-最差法(BWM)建立了融合先验地质特征权重的集成学习智能预测模型,以强化模型预测效果。之后,使用从全局到局部,从特征到样本的多尺度多维度可解释性方法,解构预测结果,定量评价预测指标重要程度。最后,结合野外验证后的专家指导校正,实现地质找矿知识更新迭代,形成矿床知识嵌入和矿床知识发现完整闭环,进而提升矿产资源智能预测决策过程的透明性和预测结果的可靠性。以四川可尔因矿集区为例进行实验,圈定A类高潜力靶区8处,占总面积的6.58%,其中84%的矿床样本位于高潜力靶区,表明预测方法的稳定性。钠长石频谱、Na_(2)O+K_(2)O、环形构造、Li/La和二云母花岗岩依次成为关键预测特征,呈现出明显的有序性,经野外验证,证实其与可尔因伟晶岩型锂矿找矿模型密切相关。
representations often exhibit opaque“black-box”characteristics.This lack of interpretability between predictions and metallogenic processes limits model generalization and reliability.To address this,we propose a knowledge-data driven interpretable prediction method.First,the Best-Worst Method(BWM)is used to derive geological feature weights for constructing an ensemble model,enhancing its performance.A multi-scale,multi-dimensional interpretability framework spanning from global to local levels and from feature-level to sample-level interpretations is then applied to deconstruct results and evaluate feature importance.Expert-guided corrections,informed by field validation,further refine the predictions,thereby forming a closed loop of knowledge embedding and discovery.This process improves workflow transparency and result reliability.Applied to the Keeryin area in Sichuan,the method identified eight high-potential Class A targets,occupying only 6.58%of the study area yet containing 84%of the known deposits.Key predictive features included remote sensing spectral response of albite/albite spectral signature,total alkali(Na_(2)O+K_(2)O)content,ring structures,Li/La ratio,and two-mica granite—as validated by their strong spatial correlation with known pegmatite-type lithium deposits in the field.
作者
李楠
尹世滔
柳炳利
肖克炎
王成辉
代鸿章
宋相龙
LI Nan;YIN Shitao;LIU Bingli;XIAO Keyan;WANG Chenghui;DAI Hongzhang;SONG Xianglong(Institute of Mineral Resources,Chinese Academy of Geological Sciences,Beijing 100037,China;School of Mathematical Sciences,Chengdu University of Technology,Chengdu 610051,China;National Key Laboratory of Deep Earth Exploration and Mineral Exploration,Institute of Mineral Resources,Chinese Academy of Geological Sciences,Beijing 100037,China;China University of Geosciences(Beijing),Beijing 100083,China)
出处
《地学前缘》
北大核心
2025年第4期60-77,共18页
Earth Science Frontiers
基金
国家重点研发计划项目(2021YFC2901905-3,2023YFC2906403)
中国地质调查局地质调查项目(DD20243233)
国家自然科学基金项目(42272347)。
关键词
矿产资源定量预测
可尔因矿集区
知识嵌入
集成学习
可解释性
野外验证
mineral resource quantitative prediction
Keeryin Mining Area
knowledge embedding
integrated learning
interpretability
field validation
