Construction and Application of the "Rock-Mineral-Spectrum" Knowledge Graph Based on Multi-Source Fusion
-
摘要: 在全球资源竞争加剧的背景下，地质资源勘查已成为多国战略布局的核心焦点，我国要提升战略性矿产的国内保障水平，强化地质资源勘查，提高资源保障能力. 随着大数据与人工智能技术的深度渗透，岩石学、光谱学与矿物学领域已积累海量多源异构数据，然而当前存在多源异构数据融合不足、知识关联薄弱、分类体系难以对齐等问题，导致了现有知识难以高效服务于资源勘查等地质应用. 因此，提出“岩石-矿物-光谱”知识图谱（rock mineral spectrum knowledge graph，RMS-KG）的系统化构建方案. 通过一体化编码遥感影像、光谱曲线、矿物特征及地质文献等多来源知识，采用自顶向下与自底向上相结合的领域本体建模策略，构建涵盖岩石分类、矿物特征和光谱特征等核心概念的知识图谱模式层. 随后，融合深度学习与语义解析技术，从结构化数据库、半结构化报告及非结构化文献中抽取相关实体、属性及关系，进而实现知识融合与语义关联，并在图数据库中完成知识融合、可视化查询与动态推理. RMS-KG包含各类实体、实体属性及关系超数万个，涵盖岩矿类型超1 000种，形成覆盖“岩石-矿物-光谱”的统一模式层与数据层，支持光谱指纹到矿物、岩石的映射以及基于矿物组合的成矿类型推理，并在“光谱导向矿物识别”和“成矿类型推理”两类场景中验证了有效性与可解释性. RMS-KG为岩矿识别与找矿预测提供可复用的知识底座与推理能力，提升地质知识的可检索、可计算与可复用性，为地质大数据的知识化表达与智能应用提供可推广范式.Abstract: Amid intensifying global competition for mineral resources, raising domestic security of strategic minerals requires higher-precision, more explainableexploration. Although petrology, spectroscopy, and mineralogy have amassed large volumes of heterogeneous data, limited cross-source fusion, weak semantic linkage, and misaligned taxonomies hinder their use in exploration. This paper proposes a systematic "Rock-Mineral-Spectrum" Knowledge Graph (RMS-KG) to address these gaps.We integrate remote-sensing imagery, reflectance spectra, mineral characteristics, and geological literature using a hybrid ontology approach that combines top-down domain modeling with bottom-updata construction. The schema covers core concepts in rock taxonomy, mineral attributes, and spectral features. Deep learning and semantic parsing extract entities, attributes, and relations from structured databases, semi-structured reports, and unstructured texts; knowledge is then fused in a graph database to enable semantic linkage, visual querying, and dynamic reasoning.RMS-KG contains on the order of tens of thousands of nodes and edges and includes more than 1, 000 rock-mineral types. It unifies the "rock-mineral-spectrum" semantics, supports mapping spectral fingerprints to minerals and rocks, and enables metallogenic-type inference from mineral assemblages. Two application scenarios, "spectrum-guided mineral identification" and "metallogenic-type inference", demonstrate its effectiveness and interpretability.RMS-KG provides a reusable knowledge substrate and reasoning capability for rock-mineral recognition and prospecting, improving the retrievability, computability, and reusability of geological knowledge and offering a generalizable paradigm for knowledge-centric geological AI.
-
Key words:
- knowledge graph /
- petrology /
- spectroscopy /
- mineralogy /
- multi-source data fusion
-
图 1 “岩石-矿物-光谱”知识图谱构建流程
Fig. 1. Construction process of rock-mineral-spectral knowledge graph
表 1 模式层概念实体、关系及属性
Table 1. Concept of entities, relationships and attributes in the pattern layer
模式层 一级实体 关系 属性 岩石类型 岩浆岩 HAS_COLOR
HAS_FORM
HAS_DRAINAGE
HAS_TEXTURE
HAS_TERRAIN
HAS_LITHOLOGY
HAS_MINERAL颜色
形态
水系特征
纹理特征
地形地貌
岩性分类
矿物特征沉积岩 变质岩 矿物类型 硅酸盐矿物 HAS_COLOR
HAS_ABS_PEAK
HAS_REF_PEAK颜色
吸收峰波长
反射峰波长碳酸盐矿物 硫酸盐矿物 硫化物矿物 氧化物矿物 光谱特征 波长 ABS_PEAK_DTH
ABS_PEAK_WTH吸收峰深度 吸收峰宽度 成矿环境 斑岩型 MINERAL_CHAR
ALTER_CHAR
SPEC_MINERAL矿物特征
蚀变特征
标型矿物热液型 岩浆型 沉积型 变质型 
下载: 导出CSV
表 2 光谱数据库介绍
Table 2. Overview of spectral databases
光谱数据库 样品与波段 关键内容 GreenPEG欧洲伟晶岩光谱库 岩矿反射光谱350~2 500 nm 原始与连续谱扣除、主吸收峰参数、样品照片、光谱矿物解释 Fregeneda-Almendra锂专题库 锂矿物与主要露头岩性 野外与实验室光谱，附坐标、蚀变、测面、设备，实验室样本含照片、CR光谱与吸收峰细节 1981—2016中国岩矿反射率数据集 多类岩矿，全国28省外业观测 光谱反射率与观测时空、仪器、波段参数等元数据，共9 348记录 PDS/RELAB矿物光谱库 矿物与Mars模拟材料 绝对反射率，两列制表符分隔，干燥环境FTIR测量
下载: 导出CSV
表 3 阈值判定规则
Table 3. Threshold determination rule
触发条件 判定结果 $ 0.6\le \mathrm{S}\mathrm{i}{\mathrm{m}}_{\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{a}\mathrm{l}} $ 判定为同一实体 $ 0.4\le \mathrm{S}\mathrm{i}{\mathrm{m}}_{\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{a}\mathrm{l}} < 0.6 $ 触发人工审核 $ \mathrm{S}\mathrm{i}{\mathrm{m}}_{\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{a}\mathrm{l}} < 0.4 $ 判定为不同实体
下载: 导出CSV
表 4 光谱特征可能对应的矿物示例
Table 4. Examples of minerals corresponding to spectral characteristics
基团 吸收峰() 可能存在矿物 H2O 1.40、1.90 高岭石、蒙脱石、云母 1.92 石英 1.93 斜长石、钾长石、亚马逊石 Al-OH 2.20 高岭石、蒙脱石、云母 Mg-OH 2.30、2.40 角闪石 OH 1.40 角闪石 1.41 石英 1.42 亚马逊石 1.90 刚玉 2.30 斜长石 2.32 黑云母 2.40 钾长石 CO32- 1.85 白云石 1.96、2.17、2.55 方解石、白云石 2.30 钾长石 2.35 方解石 2.36 黑云母 Fe2+ 0.45、1.10 刚玉 0.95 斜长石 1.00 橄榄石 1.15 亚马逊石、刚玉 1.85 石英、方解石 Fe3+ 0.86 钾长石 0.50、0.90 褐铁矿、针铁矿、赤铁矿
下载: 导出CSV
表 5 成矿环境规则
Table 5. Metallogenic environment rules
序号 规则内容 规则1 若矿物组合中含有碳酸盐矿物，如方解石、白云石等，则排除斑岩型铜矿成矿环境 规则2 当矿物组合出现“黄铁矿+黄铜矿+石英”时，应优先考虑斑岩型铜矿与热液型铜矿成矿环境 规则3 若矿物组合呈现“赤铁矿+针铁矿+方解石”时，则应优先考虑沉积型铁矿成矿环境 规则4 若矿物组合中出现橄榄石、铬铁矿或铂族矿物等特征性矿物，应优先考虑岩浆型成矿环境 规则5 若矿物组合中出现红柱石、蓝晶石、矽线石等特征变质矿物，或石墨、石棉等非金属矿物，则考虑变质型成矿环境 规则6 若矿物组合中出现三水铝石、硬水铝石等铝土矿矿物，或稀土元素矿物与黏土矿物共生，且位于地表风化带，则优先考虑风化型成矿环境
下载: 导出CSV
-
Brodaric, B., Richard, S. M., 2021. The GeoScience Ontology Reference. Geological Survey of Canada, Open File, 8796, 34. Natural Resources Canada. https://doi.org/10.4095/328296 Chen, Y., Tian, M., Wu, Q. R., et al., 2024. A Deep Learning-Based Method for Deep Information Extraction from Multimodal Data for Geological Reports to Support Geological Knowledge Graph Construction. Earth Science Informatics, 17(3): 1867-1887. https://doi.org/10.1007/s12145-023-01207-0 Ding, Y., Teng, F., Zhang, P., et al., 2021. Research on Text Information Mining Technology of Substation Inspection Based on Improved Jieba. 2021 International Conference on Wireless Communications and Smart Grid (ICWCSG). August 13-15, 2021, Hangzhou, China. IEEE: 561-564. https://doi.org/10.1109/ICWCSG53609.2021.00119 Enkhsaikhan, M., Holden, E. J., Duuring, P., et al., 2021. Understanding Ore-Forming Conditions Using Machine Reading of Text. Ore Geology Reviews, 135: 104200. https://doi.org/10.1016/j.oregeorev.2021.104200 Guan, S. P., Jin, X. L., Jia, Y. T., et al., 2018. Knowledge Reasoning over Knowledge Graph: a Survey. Journal of Software, 29(10): 2966-2994(in Chinese with English abstract). Garcia, L. F., Abel, M., Perrin, M., et al., 2020. The GeoCore Ontology: a Core Ontology for General Use in Geology. Computers & Geosciences, 135: 104387. https://doi.org/10.1016/j.cageo.2019.104387 Hu, X. M., Xu, Y. W., Ma, X. G., et al., 2023. Knowledge System, Ontology, and Knowledge Graph of the Deep-Time Digital Earth (DDE): Progress and Perspective. Journal of Earth Science, 34(5): 1323-1327. https://doi.org/10.1007/s12583-023-1930-1 Jin, X. B., Shen, L., Huang, X. J., et al., 2024. Empowering High-Quality Management of Natural Resources with New Quality Productive Forces: Logic and Path. Journal of Natural Resources, 39(9): 2011-202(in Chinese with English abstract). doi: 10.31497/zrzyxb.20240901 Kong, J. Y., Gao, Y. R., Zhang, Y. J., et al., 2021. Improved Attention Mechanism and Residual Network for Remote Sensing Image Scene Classification. IEEE Access, 9: 134800-134808. https://doi.org/10.1109/ACCESS. 2021.3116968 doi: 10.1109/ACCESS.2021.3116968 Li, D. R., Wang, S. L., Shi, W. Z., et al., 2001. On Spatial Data Mining and Knowledge Discovery (SDMKD). Geomatics and Information Science of Wuhan University, 26(6): 491-499(in Chinese with English abstract). Liu, G. Q., Gong, R. B., Shi, Y. J., et al., 2022. Construction of Well Logging Knowledge Graph and Intelligent Identification Method of Hydrocarbon-Bearing Formation. Petroleum Exploration and Development, 49(3): 502-512 (in Chinese with English abstract). doi: 10.1016/S1876-3804(22)60042-9 Lei, X. Y., Song, W. J., Fan, R. Y., et al., 2023. Semi-Supervised Geological Disasters Named Entity Recognition Using few Labeled Data. GeoInformatica, 27(2): 263-288. https://doi.org/10.1007/s10707-022-00474-1 Le, B. M. J., Streckeisen, A. L., 1991. The IUGS Systematics of Igneous Rocks. Journal of the Geological Society, 148(5): 825-833. https://doi.org/10.1144/gsjgs.148.5.0825 Liu, Q., Li, Y., Duan, H., et al., 2016. Knowledge Graph Construction Techniques. Journal of Computer Research and Development, 53(3): 582-600(in Chinese with English abstract). Ma, X. G., 2022. Knowledge Graph Construction and Application in Geosciences: a Review. Computers & Geosciences, 161: 105082. https://doi.org/10.1016/j.cageo.2022.105082 Mao, J. W., Zhang, J. D., Pirajno, F., et al., 2011. Porphyry Cu-Au-Mo-Epithermal Ag-Pb-Zn-Distal Hydrothermal Au Deposits in the Dexing Area, Jiangxi Province, East China: A Linked Ore System. Ore Geology Reviews, 43(1): 203-216. https://doi.org/10.1016/j.oregeorev.2011.08.005 Mikolov, T., Chen, K., Corrado, G., et al., 2013. Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv: 1301.3781. https://doi.org/10.48550/arXiv.1301.3781 Niu, F. G., Zhang, B., Chen, S., 2024. Review and Perspective of Earth Science Knowledge Graph in Big Data Era. Acta Seismologica Sinica, 46(3): 353-376 (in Chinese with English abstract). Qiu, Q. J., Wang, B., Ma, K., et al., 2023. A Practical Approach to Constructing a Geological Knowledge Graph: a Case Study of Mineral Exploration Data. Journal of Earth Science, 34(5): 1374-1389. https://doi.org/10.1007/s12583-023-1809-3 Qiu, Q. J., Wu, L., Ma, K., et al., 2023. A Knowledge Graph Construction Method for Geohazard Chain for Disaster Emergency Response. Earth Science, 48(5): 1875-1891(in Chinese with English abstract). Shen, Z. H., Zhu, X. J., Wang, H. J., et al., 2024. Research Data Network: Concept, Systems and Applications. Frontiers of Data & Computing, 6(4): 3-21(in Chinese with English abstract). Song, M. C., Ding, Z. J., Zhang, J. J., et al., 2021. Geology and Mineralization of the Sanshandao Supergiant Gold Deposit (1 200 t) in the Jiaodong Peninsula, China: a Review. China Geology, 4(4): 686-719. https://doi.org/10.31035/cg2021070 Song, Y. C., Liu, Y. C., Hou, Z. Q., et al., 2019. Sediment-Hosted Pb-Zn Deposits in the Tethyan Domain from China to Iran: Characteristics, Tectonic Setting, and Ore Controls. Gondwana Research, 75: 249-281. https://doi.org/10.1016/j.gr.2019.05.005 Tian, J. P., Wang, J. H., Tian, T. L., et al., 2024. In-Situ Geochemical and Rb-Sr Dating Analysis of Sulfides from a Gold Deposit Offshore of Northern Sanshandao, Jiaodong Peninsula, North China: Implications for Gold Mineralization. Minerals, 14(5): 456. https://doi.org/10.3390/min14050456 Velickovic, P., Cucurull, G., Casanova, A., et al., 2017. Graph Attention Networks. Stat, 1050(20): 10-48550. Wang, C. S., Hazen, R. M., Cheng, Q. M., et al., 2021. The Deep-Time Digital Earth Program: Data-Driven Discovery in Geosciences. National Science Review, 8(9): nwab027. https://doi.org/10.1093/nsr/nwab027 Wu, L. X., Mao, W. F., Liu, S. J., et al., 2018. Mechanism of Infrared and Microwave Radiation Variation of Rock Stress and Key Problems of In-Situ Stress Remote Sensing. National Remote Sensing Bulletin, 22(S1): 146-161(in Chinese with English abstract). doi: 10.11834/jrs.20187256 Wang, M., 2018. Metallogenic Type and Prospecting Characteristics of Bauxite in a Certain Area. World Nonferrous Metals, 43(12): 102-103 (in Chinese with English abstract). Xu, Q., Cui, S. H., Huang, W., et al., 2023. Construction of a Landslide Knowledge Graph in the Field of Engineering Geology. Geomatics and Information Science of Wuhan University, 48(10): 1601-1615(in Chinese with English abstract). Xu, L. Q., Zhang, T., Zhang, M., et al., 2016. Summary of Ore f Regularity of Important Mineral Resources in Inner Mongolia. Mineral Deposits, 35(5): 966-980(in Chinese with English abstract). Xie, T., Yang, J. A., Liu, H., 2020. Chinese Entity Recognition Based on BERT-BiLSTM-CRF Model. Computer Systems & Applications, 29(7): 48-55(in Chinese with English abstract). Ye, X., Shen, H., Ma, X., et al., 2016. From Word Embeddings to Document Similarities for Improved Information Retrieval in Software Engineering. Proceedings of the 38th International Conference on Software Engineering. Austin Texas, . ACM, 404-415. https://doi.org/10.1145/2884781.2884862 Zhai, M. G., Yang, S. F., Chen, N. H., et al., 2018. Big Data Epoch: Challenges and Opportunities for Geology. Bulletin of Chinese Academy of Sciences, 33(8): 825-831(in Chinese with English abstract). Zhou, C. H., Wang, H., Wang, C. S., et al., 2021. Research on Geoscience Knowledge Graph in the Era of Big Data. Chinese Science: Earth Sciences, 51(7): 1070-1079 (in Chinese). Zhang, C. J., Liu, W. C., Zhang, X. Y., et al., 2023. Knowledge Graph Construction Method of Gold Mine Based on Ontology. Journal of Geo-Information Science, 25(7): 1269-1281(in Chinese with English abstract). Zhou, Y. Z., Zhang, Q. L., Huang, Y. J., et al., 2021. Constructing Knowledge Graph for the Porphyry Copper Deposit in the Qingzhou-Hangzhou Bay Area: Insight into Knowledge Graph based Mineral Resource Prediction and Evaluation. Earth Science Frontiers, 28(3): 67-75 (in Chinese with English abstract). Zhang, Q. L., Zhou, Y. Z., Yu, P. P., et al., 2024. Ontology Construction of Multi-Level Ore Deposit and Its Application in Knowledge Graph. Bulletin of Mineralogy, Petrology and Geochemistry, 43(1): 211-217(in Chinese with English abstract). Zhao, Z. F., Han, S. K., So, I. M., 2018. Architecture of Knowledge Graph Construction Techniques. International Journal of Pure and Applied Mathematics, 118(19): 1869-1883. Zhang, F., Yang, L. Y., Li, J. W., et al., 2022. An Overview of Entity Alignment Methods. Chinese Journal of Computers, 45(6): 1195-1225(in Chinese with English abstract). 官赛萍, 靳小龙, 贾岩涛, 等, 2018. 面向知识图谱的知识推理研究进展. 软件学报, 29(10): 2966-2994. 金晓斌, 沈镭, 黄贤金, 等, 2024. 新质生产力赋能自然资源高质量管理: 逻辑与路径. 自然资源学报, 39(9): 2011-2028. 李德仁, 王树良, 史文中, 等, 2001. 论空间数据挖掘和知识发现. 武汉大学学报(信息科学版), 26(6): 491-499. 刘国强, 龚仁彬, 石玉江, 等, 2022. 油气层测井知识图谱构建及其智能识别方法. 石油勘探与开发, 49(3): 502-512. 刘峤, 李杨, 段宏, 等, 2016. 知识图谱构建技术综述. 计算机研究与发展, 53(3): 582-600. 牛凤桂, 张贝, 陈石, 2024. 大数据时代的地球科学知识图谱研究现状与展望. 地震学报, 46(3): 353-376. 邱芹军, 吴亮, 马凯, 等, 2023. 面向灾害应急响应的地质灾害链知识图谱构建方法. 地球科学, 48(5): 1875-1891. doi: 10.3799/dqkx.2022.313 王梅, 2018. 某区铝土矿成矿类型以及找矿特点初探. 世界有色金属, 43(12): 102-103. 吴立新, 毛文飞, 刘善军, 等, 2018. 岩石受力红外与微波辐射变化机理及地应力遥感关键问题. 遥感学报, 22(S1): 161. 许强, 崔圣华, 黄维, 等, 2023. 面向工程地质领域的滑坡知识图谱构建方法研究. 武汉大学学报(信息科学版), 48(10): 1601-1615. 许立权, 张彤, 张明, 等, 2016. 内蒙古自治区重要矿种成矿规律综述. 矿床地质, 35(5): 966-980. 谢腾, 杨俊安, 刘辉, 2020. 基于BERT-BiLSTM-CRF模型的中文实体识别. 计算机系统应用, 29(7): 48-55. 翟明国, 杨树锋, 陈宁华, 等, 2018. 大数据时代: 地质学的挑战与机遇. 中国科学院院刊, 33(8): 825-831. 周成虎, 王华, 王成善, 等, 2021. 大数据时代的地学知识图谱研究. 中国科学: 地球科学, 51(7): 1070-1079. 张春菊, 刘文聪, 张雪英, 等, 2023. 基于本体的金矿知识图谱构建方法. 地球信息科学学报, 25(7): 1269-1281. 周永章, 张前龙, 黄永健, 等, 2021. 钦杭成矿带斑岩铜矿知识图谱构建及应用展望. 地学前缘, 28(3): 67-75. 张前龙, 周永章, 虞鹏鹏, 等, 2024. 多层次矿床本体的构建及在知识图谱中的应用. 矿物岩石地球化学通报, 43(1): 211-217. 张富, 杨琳艳, 李健伟, 等, 2022. 实体对齐研究综述. 计算机学报, 45(6): 1195-1225. -
点击查看大图
图(7) / 表(5)
计量
- 文章访问数: 315
- HTML全文浏览量: 52
- PDF下载量: 47
- 被引次数: 0
