成都理工大学学报（自然科学版）2025，Vol.52Issue(5)：827-843,17.DOI:10.12474/cdlgzrkx.2025071601
矿产勘查知识图谱——研究进展、关键问题与未来展望
Knowledge graphs for mineral exploration:Research progress,key challenges,and future perspectives
摘要
Abstract
As a complex task that heavily relies on causal reasoning and expert knowledge,mineral exploration urgently requires a computable framework for knowledge representation and reasoning centered on metallogenic processes.With the widespread application of big data and artificial intelligence in geosciences,knowledge graphs have gradually become an important tool for integrating multisource geological data,explicitly representing metallogenic processes and supporting the prediction of mineral exploration targets.This study systematically reviews the research progress of knowledge graphs in the context of mineral exploration,focusing on ontological modeling,semantic integration,and reasoning mechanisms.It also highlights the application paths and challenges of graph neural networks in graph-structured representation and mineral target prediction.Although knowledge graphs demonstrate significant advantages in modeling causal chains and enabling explainable predictions,there remain critical bottlenecks in unified ontological standards,cross-modal data fusion,model interpretability,and engineering deployment.Furthermore,current research still depends heavily on expert knowledge,lacking robust cross-modal fusion frameworks and standardized ontologies,which limit their practical applications in mineral prospecting.Looking forward,the deep integration of knowledge,data,and models is recommended,which should enable researchers to explore the collaborative reasoning of symbolic logic,neural networks,and large language models,and to develop general-purpose knowledge graphs and service-oriented platforms for mineral exploration.关键词
矿产勘查/知识图谱/图神经网络/本体建模/知识推理Key words
mineral exploration/knowledge graph/graph neural networks/ontological modeling/knowledge reasoning分类
天文与地球科学引用本文复制引用
周仲礼,柳炳利,龚成杰,曹昌杰,孔韫辉,李程,但诗瑶,王政尧..矿产勘查知识图谱——研究进展、关键问题与未来展望[J].成都理工大学学报（自然科学版）,2025,52(5):827-843,17.基金项目
国家重点研发计划课题(2023YFC2906403) （2023YFC2906403）
四川省自然科学基金(2024NSFSC0009) （2024NSFSC0009）
紫金矿业集团横向委托项目(4502-FW-2024-00055) （4502-FW-2024-00055）
新疆维吾尔自治区重点研发计划课题(2024B03009-3,2024B03011-3). （2024B03009-3,2024B03011-3）
