融合知识图谱的矿产资源定量预测  

Knowledge graph-infused quantitative mineral resource forecasting

作　　者：王成彬 王明果[1,2] 王博[1] 陈建国 马小刚[4] 蒋恕[3] WANG Chengbin;WANG Mingguo;WANG Bo;CHEN Jianguo;MA Xiaogang;JIANG Shu(State Key Laboratory of Geological Processes and Mineral Resources/Ministry of Natural Resources Key Laboratory of Resource Quantita-tive Evaluation and Information Engineering,China University of Geosciences(Wuhan),Wuhan 430074,China;Yunnan Geological Big Data Center,Geological Survey and Mapping Institute of Yunnan Province,Kunming 650218,China;School of Earth Resources,China University of Geosciences(Wuhan),Wuhan 430074,China;Department of Computer Sciences,University of Idaho,Moscow 83844-1010,USA)

机构地区：[1]中国地质大学(武汉)地质过程与矿产资源国家重点实验室/自然资源部资源定量评价与信息工程重点实验室,湖北武汉430074 [2]云南省地矿测绘院有限公司云南地质大数据中心,云南昆明650218 [3]中国地质大学(武汉)资源学院,湖北武汉430074 [4]爱达荷大学计算机系,美国爱达荷州莫斯科83844-1010

出　　处：《地学前缘》2024年第4期26-36,共11页Earth Science Frontiers

基　　金：国家重点研发计划项目(2022YFF0801202,2023YFC2906404,2022YFF0801201);国家自然科学基金项目(41902305);新疆维吾尔自治区重点专项(2022A03009-3);战略性矿产资源潜力智能评价湖北省创新群体项目(2023AFA001);“云找矿”应用支撑能力技术研究项目(YNGH[2023]-155)。

摘　　要：大数据和人工智能极大地促进了矿产勘查的发展,创新了矿产预测研究范式,提升了地质找矿大数据的挖掘与集成能力。在资源定量预测领域,知识-数据联合驱动的综合信息智能预测已逐渐成为行业共识,如何实现数据和知识联合驱动是目前亟待解决的问题。知识图谱可以整合多源、异构的地质找矿大数据,其中蕴含的知识和规则在驱动地球科学领域的知识发现方面具有重要的发展潜力。本文针对大数据和人工智能时代对资源定量预测智能化和自动化的需求,结合知识图谱相关技术的特点,探讨融合知识图谱技术的矿产资源定量预测智能化和自动化的可行性和技术方法路线。重点剖析面向矿产预测的成矿-勘查系统多时序全要素知识图谱构建和基于知识图谱从“求同”和“求异”的角度建立找矿预测模型,知识图谱中的知识嵌入到地物化遥异常信息提取的方法,以及融合知识图谱的资源定量预测工作的机遇和挑战。拟希望将知识图谱中知识表达和推理融入到矿产资源定量预测技术方法流程中,协助地质专家来确定矿产预测模型,提高矿产预测的自动化和智能化。Big data and artificial intelligence have greatly transformed mineral exploration practices with the development of innovative mineral forecasting models and improvement of forecasting efficiency for strategic minerals.In the field of quantitative mineral forecasting,comprehensive intelligent forecasting by combining knowledge and data has gradually become a common consensus,however,the challenge lies in how to combine knowledge and data.Knowledge graphs integrate multi-source,heterogeneous geoscience big data and drive knowledge discovery through rules and reasoning.Here,we discuss the feasibility and technical roadmap of knowledge graph-infused intelligent and automated mineral resource forecasting,particularly in consideration of the characteristics of knowledge graphs in the era of big data and artificial intelligence.We focus mainly on the construction of multi-temporal,all-element knowledge graphs for mineral deposit-mineral exploration systems and the methodology for establishing forecasting models from the perspectives of ore commonality and distinctiveness based on knowledge graphs.The opportunities and challenges of knowledge graph embedding for geological anomaly information extraction and quantitative resource forecasting are also discussed,in the hope that the infusion of knowledge representation and reasoning from knowledge graphs into the technical workflow of quantitative mineral resource forecasting can aid geologists in building ore forecasting models and enhancing automated and intelligent mineral forecasting.

关 键 词：知识图谱 资源定量预测 矿产预测智能化 地质大数据 

分 类 号：P628[天文地球—地质矿产勘探] P612[天文地球—地质学] TP18[自动化与计算机技术—控制理论与控制工程]