融合知识图谱的矿产资源定量预测

doi:10.13745/j.esf.sf.2024.5.3

地学前缘 ›› 2024, Vol. 31 ›› Issue (4): 26-36.DOI: 10.13745/j.esf.sf.2024.5.3

融合知识图谱的矿产资源定量预测

王成彬¹^,³(), 王明果¹^,², 王博¹, 陈建国¹^,³, 马小刚⁴, 蒋恕³

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

收稿日期:2023-09-01 修回日期:2024-02-29 出版日期:2024-07-25 发布日期:2024-07-10
作者简介:王成彬(1988—),男,博士,副教授,主要从事地学知识图谱构建与智慧应用、数学地质与地质信息方面研究工作。E-mail: wangchb@cug.edu.cn
基金资助:
国家重点研发计划项目(2022YFF0801202);国家重点研发计划项目(2023YFC2906404);国家重点研发计划项目(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)

Knowledge graph-infused quantitative mineral resource forecasting

WANG Chengbin¹^,³(), WANG Mingguo¹^,², WANG Bo¹, CHEN Jianguo¹^,³, MA Xiaogang⁴, JIANG Shu³

1. State Key Laboratory of Geological Processes and Mineral Resources/Ministry of Natural Resources Key Laboratory of Resource Quantitative Evaluation and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430074, China
2. Yunnan Geological Big Data Center, Geological Survey and Mapping Institute of Yunnan Province, Kunming 650218, China
3. School of Earth Resources, China University of Geosciences (Wuhan), Wuhan 430074, China
4. Department of Computer Sciences, University of Idaho, Moscow 83844-1010, USA

Received:2023-09-01 Revised:2024-02-29 Online:2024-07-25 Published:2024-07-10

摘要/Abstract

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。

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

Abstract:

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.

Key words: knowledge graph, mineral resource quantitative forecasting, intelligent mineral forecasting, geological big data

中图分类号:

王成彬, 王明果, 王博, 陈建国, 马小刚, 蒋恕. 融合知识图谱的矿产资源定量预测[J]. 地学前缘, 2024, 31(4): 26-36.

WANG Chengbin, WANG Mingguo, WANG Bo, CHEN Jianguo, MA Xiaogang, JIANG Shu. Knowledge graph-infused quantitative mineral resource forecasting[J]. Earth Science Frontiers, 2024, 31(4): 26-36.

图/表 6

图1 知识图谱技术发展历史(据文献[8]修改)

Fig.1 Development of knowledge graph technology. Modified after [8].

图2 矿床位置信息的图表达

Fig.2 Graph representation of locality of mineral deposits

图3 用例驱动的成矿-勘查系统本体模型构建(据文献[70])

Fig.3 Ontology construction of a mineralization-exploration system using a case-driven method.Adapted from[70].

图4 基于知识图谱矿产预测模型构建

Fig.4 Constructing a mineral forecasting model based on a knowledge graph

图5 不同聚类数的轮廓系数

Fig.5 Plot of group number vs. silhouette coefficient

图6 知识图谱中蕴含的深层次异常信息提取和整合

Fig.6 Extraction and integration of deep-level anomaly information contained in a knowledge graph

参考文献 70

[1]	陈建平, 李靖, 谢帅, 等. 中国地质大数据研究现状[J]. 地质学刊, 2017, 41(3): 353-366.
[2]	周永章, 黎培兴, 王树功, 等. 矿床大数据及智能矿床模型研究背景与进展[J]. 矿物岩石地球化学通报, 2017, 36(2): 327-331, 344.
[3]	周永章, 陈川, 张旗, 等. 地质大数据分析的若干工具与应用[J]. 大地构造与成矿学, 2020, 44(2): 173-182.
[4]	周永章, 陈烁, 张旗, 等. 大数据与数学地球科学研究进展: 大数据与数学地球科学专题代序[J]. 岩石学报, 2018, 34(2): 255-263.
[5]	翟明国, 杨树锋, 陈宁华, 等. 大数据时代: 地质学的挑战与机遇[J]. 中国科学院院刊, 2018, 33(8): 825-831.
[6]	QIU Q J, MA K, LV H R, et al. Construction and application of a knowledge graph for iron deposits using text mining analytics and a deep learning algorithm[J]. Mathematical Geosciences, 2023, 55(3): 423-456.
[7]	QIU Q J, XIE Z, MA K, et al. BERTCWS: unsupervised multi-granular Chinese word segmentation based on a BERT method for the geoscience domain[J]. Annals of GIS, 2023, 29(3): 387-399.
[8]	WANG C B, LI Y J, CHEN J G. Text mining and knowledge graph construction from geoscience literature legacy: a review[R]// MA X, MOOKERJEE M, HSU L, et al. Recent advancement in geoinformatics and data science. Boulder, Colorado: Geological Society of America, 2023: 11-28.
[9]	WANG C B, MA X G, CHEN J G, et al. Information extraction and knowledge graph construction from geoscience literature[J]. Computers and Geosciences, 2018, 112: 112-120.
[10]	WANG C B, LI Y J, CHEN J G, et al. Named entity annotation schema for geological literature mining in the domain of porphyry copper deposits[J]. Ore Geology Reviews, 2023, 152: 105243.
[11]	HART P E, DUDA R O, EINAUDI M T. Prospector: a computer-based consultation system for mineral exploration[J]. Journal of the International Association for Mathematical Geology, 1978, 10(5): 589-610.
[12]	张东晓. 科学机器学习中的知识嵌入与知识发现[R/OL]. (2023-01-28)[2024-01-15]. https://www.jiqizhixin.com/articles/2023-01-28-2.
[13]	吴飞. 数据驱动与知识引导相互结合的智能计算[J]. 智能系统学报, 2022, 17(1): 217-219.
[14]	SINGHAL A. Official Google Blog: introducing the knowledge graph: things, not strings[R/OL]. (2015-01-02)[2023-12-04]. https://www.mendeley.com/catalogue/ca10852b-1f48-3172-9b4f-8b521878b39d/.
[15]	BRODARIC B, GAHEGAN M. Representing geoscientific knowledge in cyberinfrastructure: some challenges, approaches, and implementations[M]//Geoinformatics: data to knowledge. Boulder, Colorado: Geological Society of America, 2006.
[16]	BERGEN K J, JOHNSON P A, DE HOOP M V, et al. Machine learning for data-driven discovery in solid Earth geoscience[J]. Science, 2019, 363(6433): eaau0323.
[17]	周成虎, 王华, 王成善, 等. 大数据时代的地学知识图谱研究[J]. 中国科学: 地球科学, 2021, 51(7): 1070-1079.
[18]	GIL Y, PIERCE S A, BABAIE H, et al. Intelligent systems for geosciences[J]. Communications of the ACM, 2018, 62(1): 76-84.
[19]	NORMILE D. Earth scientists plan a ‘geological Google’[J]. Science, 2019, 363(6430): 917.
[20]	REICHSTEIN M, CAMPS-VALLS G, STEVENS B, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019, 566(7743): 195-204.
[21]	PETERS S E, ZHANG C, LIVNY M, et al. A machine reading system for assembling synthetic paleontological databases[J]. PLoS One, 2014, 9(12): e113523.
[22]	HUSSON J M, PETERS S E, ROSS I, et al. Macrostrat and GeoDeepDive: a platform for geological data integration and deep-time research[C/OL]// Proceedings of the AGU fall meeting 2016 abstracts. San Francisco: American Geophysical Union, 2016[2023-09-01]. https://agu.confex.com/agu/fm16/meetingapp.cgi/Paper/187029.
[23]	ZHANG C. DeepDive: a data management system for automatic knowledge base construction[D]. Madison, WI: The University of Wisconsin-Madison, 2015.
[24]	KOSKELA R, RAMAMURTHY M, PEARLMAN J, et al. Earthcube: a community-driven cyberinfrastructure for the geosciences[C/OL]// Proceedings of 19th EGU general assembly conference abstracts. Vienna, Austria: European Geosciences Union, 2017: 5884[2023-06-15]. https://meetingorganizer.copernicus.org/EGU2017/EGU2017-5884-1.pdf.
[25]	成秋明. 深时数字地球: 全球古地理重建与深时大数据[J]. 国际学术动态, 2019(6): 28-29.
[26]	WANG C S, HAZEN R M, CHENG Q M, et al. The Deep-Time Digital Earth program: data-driven discovery in geosciences[J]. National Science Review, 2021, 8(9): nwab027.
[27]	STEPHENSON M H, CHENG Q M, WANG C S, et al. Progress towards the establishment of the IUGS Deep-time Digital Earth (DDE) programme[J]. Episodes, 2020, 43(4): 1057-1062.
[28]	MA X G, MA C, WANG C B. A new structure for representing and tracking version information in a deep time knowledge graph[J]. Computers and Geosciences, 2020, 145: 104620.
[29]	RASKIN R G, PAN M J. Knowledge representation in the semantic web for Earth and environmental terminology (SWEET)[J]. Computers and Geosciences, 2005, 31(9): 1119-1125.
[30]	COX S J D, RICHARD S M. A geologic timescale ontology and service[J]. Earth Science Informatics, 2015, 8(1): 5-19.
[31]	WANG C B, MA X G, CHEN J G. Ontology-driven data integration and visualization for exploring regional geologic time and paleontological information[J]. Computers and Geosciences, 2018, 115: 12-19.
[32]	MENTES H. Design and development of a mineral exploration ontology[D]. Atlanta, GA: Georgia State University, 2012.
[33]	WANG C B, TAN L Q, LI Y J, et al. Ontology-driven relational data mapping for constructing a knowledge graph of porphyry copper deposits[J]. Earth Science Informatics, 2024: 1-12. https://doi.org/10.1007/s12145-024-01307-5.
[34]	李国和, 杨新颖, 叶婷, 等. 海相油气地质的概念本体知识系统设计与实现[J]. 计算机应用, 2010, 30(2): 532-536.
[35]	匡立春, 刘合, 任义丽, 等. 人工智能在石油勘探开发领域的应用现状与发展趋势[J]. 石油勘探与开发, 2021, 48(1): 1-11. DOI
[36]	BABAIE H A, OLDOW J S, BABAEI A, et al. Designing a modular architecture for the structural geology ontology[M]//Geoinformatics: data to knowledge. Boulder, Colorado: Geological Society of America, 2006. 2006.
[37]	ZHONG J, AYDINA A, MCGUINNESS D L. Ontology of fractures[J]. Journal of Structural Geology, 2009, 31(3): 251-259.
[38]	MANTOVANI A, PIANA F, LOMBARDO V. Ontology-driven representation of knowledge for geological maps[J]. Computers and Geosciences, 2020, 139: 104446.
[39]	LIU G, WANG Y N, WU C L. Research and application of geological hazard domain ontology[C/OL]// 2010 18th international conference on geoinformatics. Beijing: IEEE, 2010: 1-6[2011-06-16]. https://www.doi.org/10.1109/GEOINFORMATICS.2010.5567498.
[40]	RUEDA C, BERMUDEZ L, FREDERICKS J. The MMI ontology registry and repository: a portal for marine metadata interoperability[C/OL]// Oceans 2009. Biloxi: IEEE, 2009: 1-6[2010-09-01]. https://www.doi.org/10.23919/OCEANS.2009.5422206.
[41]	黄刚. 知识图谱构建方法及其在油气勘探开发领域应用研究[D]. 大庆: 东北石油大学, 2019.
[42]	QIU Q J, XIE Z, WU L, et al. BiLSTM-CRF for geological named entity recognition from the geoscience literature[J]. Earth Science Informatics, 2019, 12(4): 565-579.
[43]	QIU Q J, XIE Z, WU L, et al. GNER: a generative model for geological named entity recognition without labeled data using deep learning[J]. Earth and Space Science, 2019, 6(6): 931-946.
[44]	QIU Q J, XIE Z, WU L. A cyclic self-learning Chinese word segmentation for the geoscience domain[J]. Geomatica, 2018, 72(1): 16-26.
[45]	HUANG L, DU Y F, CHEN G Y. GeoSegmenter: a statistically learned Chinese word segmenter for the geoscience domain[J]. Computers and Geosciences, 2015, 76: 11-17.
[46]	LI S, CHEN J P, XIANG J. Prospecting information extraction by text mining based on convolutional neural networks: a case study of the lala copper deposit, China[J]. IEEE Access, 2018, 6: 52286-52297.
[47]	ZHU Y Q, ZHOU W W, XU Y, et al. Intelligent learning for knowledge graph towards geological data[J]. Scientific Programming, 2017, 2017: 5072427.
[48]	王永志, 金樑, 朱月琴, 等. 基于大数据技术的地学文档关键词提取算法研发[J]. 地球物理学进展, 2018, 33(3): 1274-1281.
[49]	QIU Q J, XIE Z, WU L, et al. Automatic spatiotemporal and semantic information extraction from unstructured geoscience reports using text mining techniques[J]. Earth Science Informatics, 2020, 13(4): 1393-1410.
[50]	ZHOU X G, GONG R B, SHI F G, et al. PetroKG: construction and application of knowledge graph in upstream area of PetroChina[J]. Journal of Computer Science and Technology, 2020, 35(2): 368-378.
[51]	HOLDEN E J, LIU W, HORROCKS T, et al. GeoDocA-Fast analysis of geological content in mineral exploration reports: a text mining approach[J]. Ore Geology Reviews, 2019, 111: 102919.
[52]	PETERS S E, HUSSON J M, WILCOTS J. The rise and fall of stromatolites in shallow marine environments[J]. Geology, 2017, 45(6): 487-490.
[53]	MOORE E K, HAO J H, PRABHU A, et al. Geological and chemical factors that impacted the biological utilization of cobalt in the Archean eon[J]. Journal of Geophysical Research: Biogeosciences, 2018, 123(3): 743-759.
[54]	赵鹏大. “三联式” 资源定量预测与评价: 数字找矿理论与实践探讨[J]. 地球科学, 2002, 27(5): 482-489.
[55]	赵鹏大. 关于数字地质[C]// 中国地质学会. 第十届全国数学地质与地学信息学术研讨会论文集. 武汉: 中国地质大学出版社, 2011.
[56]	周永章, 左仁广, 刘刚, 等. 数学地球科学跨越发展的十年: 大数据、人工智能算法正在改变地质学[J]. 矿物岩石地球化学通报, 2021, 40(3): 556-573.
[57]	左仁广. 基于数据科学的矿产资源定量预测的理论与方法探索[J]. 地学前缘, 2021, 28(3): 49-55. DOI
[58]	左仁广, 彭勇, 李童, 等. 基于深度学习的地质找矿大数据挖掘与集成的挑战[J]. 地球科学, 2021(1): 350-358.
[59]	赵鹏大. 大数据时代数字找矿与定量评价[J]. 地质通报, 2015, 34(7): 1255-1259.
[60]	张金川, 陈世敬, 李中明, 等. 页岩气资源智能评价[J]. 油气藏评价与开发, 2021, 11(4): 476-486.
[61]	肖克炎, 孙莉, 李楠, 等. 大数据思维下的矿产资源评价[J]. 地质通报, 2015, 34(7): 1266-1272.
[62]	WÓJCIK S, OSMAN T, ZAWADA P. Semanticapproach for prospectivity analysis of mineral deposits[C]// Proceedings of the 2nd international conference on geographical information systems theory, applications and management. Rome, Italy: Science and Technology Press, 2016: 180-189.
[63]	MCGREGOR J, SMYTH C, POOLE D. Ontology-based reasoning applications for mineral exploration and hazard mapping[C/OL]// Proceedings of 21th EGU general assembly conference abstracts, Vienna, Austria: European Geosciences Union, 2019: 11552[2020-02-16]. https://ui.adsabs.harvard.edu/abs/2019EGUGA..2111552M/abstract.
[64]	周永章, 张前龙, 黄永健, 等. 钦杭成矿带斑岩铜矿知识图谱构建及应用展望[J]. 地学前缘, 2021, 28(3): 67-75. DOI
[65]	杨明莉, 薛林福, 冉祥金, 等. 智能矿产地质调查方法: 以甘肃大桥-崖湾地区为例[J]. 岩石学报, 2021, 37(12): 3880-3892.
[66]	LI S, CHEN J P, LIU C. Overview on the development of intelligent methods for mineral resource prediction under the background of geological big data[J]. Minerals, 2022, 12(5): 616.
[67]	LI S, LIU C, CHEN J. Mineral prospecting prediction via transfer learning based on geological big data: a case study of Huayuan, Hunan, China[J]. Minerals, 2023, 13(4): 504.
[68]	吴永亮, 贾志杰, 陈建平, 等. 基于大数据智能的找矿模型构建与预测[J]. 中国矿业, 2017, 26(9): 79-84.
[69]	LAWLEY C J M, GADD M G, PARSA M, et al. Applications of natural language processing to geoscience text data and prospectivity modeling[J]. Natural Resources Research, 2023, 32(4): 1503-1527.
[70]	罗转霞. 云南省锡矿领域语义关系抽取及知识图谱构建[D]. 武汉: 中国地质大学(武汉), 2023.

融合知识图谱的矿产资源定量预测

Knowledge graph-infused quantitative mineral resource forecasting

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 70

相关文章 11

编辑推荐

Metrics

本文评价

[1]	朱彪彪, 曹伟, 虞鹏鹏, 张前龙, 郭兰萱, 原桂强, 韩枫, 王汉雨, 周永章. 基于CiteSpace的地质大数据与人工智能研究热点及前沿分析[J]. 地学前缘, 2024, 31(4): 73-86.
[2]	张前龙, 周永章, 郭兰萱, 原桂强, 虞鹏鹏, 王汉雨, 朱彪彪, 韩枫, 龙师尧. 找矿知识图谱的智能化应用:以钦杭成矿带斑岩铜矿为例[J]. 地学前缘, 2024, 31(4): 7-15.
[3]	曹胜桃, 胡瑞忠, 周永章, 刘建中, 谭亲平, 高伟, 郑禄林, 郑禄璟, 宋威方. 基于大数据关联规则算法的卡林型金矿床元素富集规律及找矿方法研究[J]. 地学前缘, 2024, 31(4): 58-72.
[4]	王岩, 王登红, 王成辉, 黎华, 刘金宇, 孙赫, 高新宇, 金雅楠, 秦燕, 黄凡. 基于地质大数据的中国金矿时空分布规律定量研究[J]. 地学前缘, 2024, 31(4): 438-455.
[5]	季晓慧, 董雨航, 杨中基, 杨眉, 何明跃, 王玉柱. 基于知识图谱多跳推理的中文矿物知识问答方法与系统[J]. 地学前缘, 2024, 31(4): 37-46.
[6]	叶育鑫, 刘家文, 曾婉馨, 叶水盛. 基于本体指导的矿产预测知识图谱构建研究[J]. 地学前缘, 2024, 31(4): 16-25.
[7]	周永章, 肖凡. 管窥人工智能与大数据地球科学研究新进展[J]. 地学前缘, 2024, 31(4): 1-6.
[8]	周永章, 张前龙, 黄永健, 杨威, 肖凡, 吉俊杰, 韩枫, 唐磊, 欧阳冲, 沈文杰. 钦杭成矿带斑岩铜矿知识图谱构建及应用展望[J]. 地学前缘, 2021, 28(3): 67-75.
[9]	左仁广. 基于数据科学的矿产资源定量预测的理论与方法探索[J]. 地学前缘, 2021, 28(3): 49-55.
[10]	刘心怡，周永章. 关联规则算法在粤西庞西垌地区元素异常组合研究中的应用 [J]. 地学前缘, 2019, 26(4): 125-130.
[11]	赵鹏大. 地质大数据特点及其合理开发利用[J]. 地学前缘, 2019, 26(4): 1-5.