钦杭成矿带斑岩铜矿知识图谱构建及应用展望

doi:10.13745/j.esf.sf.2021.1.2

地学前缘 ›› 2021, Vol. 28 ›› Issue (3): 67-75.DOI: 10.13745/j.esf.sf.2021.1.2

• 数学地质与矿产定量勘查 • 上一篇下一篇

钦杭成矿带斑岩铜矿知识图谱构建及应用展望

周永章¹^,²(), 张前龙¹^,², 黄永健³, 杨威⁴, 肖凡¹^,²^,⁵, 吉俊杰¹^,²^,⁵, 韩枫¹^,²^,⁵, 唐磊¹^,²^,⁵, 欧阳冲¹^,²^,⁵, 沈文杰¹^,²^,⁵

1.中山大学地球环境与地球资源研究中心, 广东广州 510275
2.中山大学地球科学与工程学院, 广东广州 510275
3.广东轩辕网络科技股份有限公司, 广东广州 510000
4.广东高质资源环境研究院, 广东广州 510000
5.广东省地质过程与矿产资源探查重点实验室, 广东广州 510275

收稿日期:2021-01-10 修回日期:2021-03-09 出版日期:2021-05-20 发布日期:2021-05-23
作者简介:周永章(1963—),男,教授,博士生导师,主要从事地球化学、大数据与数学地球科学专业。E-mail: zhouyz@mail.sysu.edu.cn
基金资助:
国家自然科学基金项目(U1911202);广东省重点研发计划项目(2020B1111370001);国家重点研发计划项目(2016YFC0600506);广东省地质过程与矿产资源探查重点实验室基金项目

Constructing knowledge graph for the porphyry copper deposit in the Qingzhou-Hangzhou Bay area: Insight into knowledge graph based mineral resource prediction and evaluation

ZHOU Yongzhang¹^,²(), ZHANG Qianlong¹^,², HUANG Yongjian³, YANG Wei⁴, XIAO Fan¹^,²^,⁵, JI Junjie¹^,²^,⁵, HAN Feng¹^,²^,⁵, TANG Lei¹^,²^,⁵, OUYANG Chong¹^,²^,⁵, SHEN Wenjie¹^,²^,⁵

1. Center for Earth Environment & Resources, Sun Yat-sen University, Guangzhou 510275, China
2. School of Earth Sciences & Geological Engineering, Sun Yat-Sen University, Guangzhou 510275, China
3. Guangdong Xuanyuan Network Tech. Inc., Guangzhou 510000, China
4. Guangdong Institute of High Quality Resources and Environment, Guangzhou 510000, China
5. Guangdong Provincial Key Lab of Geological Processes and Mineral Resource Survey, Guangzhou 510275, China

Received:2021-01-10 Revised:2021-03-09 Online:2021-05-20 Published:2021-05-23

摘要/Abstract

摘要：

知识图谱使用人与机器能共同理解的语言,以“图”的方式来描述真实世界,是人工智能研究的重要方向之一。本研究是构建单体矿床、成矿系列和重要成矿区(带)的知识图谱实验的一部分,收集了钦杭成矿带6个较为典型的斑岩铜矿、斑岩-夕卡岩型铜矿的原始文本数据,参照斑岩铜矿床概念模型进行知识获取,标注、抽提文本中的实体、关系、属性,构建了具备基本应用功能的斑岩铜矿床知识图谱。基于未来矿产资源预测评价应充分理解地球系统、成矿系统、勘查系统、预测评价系统相互关系的认识,讨论了建立“地球系统-成矿系统-勘查系统-预测评价系统”关联知识图谱体系需要解决的关键科学技术问题,包括“地-矿-勘-评系统”领域本体及知识图谱递进关联体系,大规模“地-矿-勘-评系统”领域本体及知识图谱的自动构建技术,基于多模态关联数据嵌入“地-矿-勘-评系统”知识图谱自演化、补全技术以及基于知识图谱、大数据挖掘和人工智能的地球系统资源预测理论与方法。

关键词: 知识图谱, 知识获取, 地质大数据, 矿产资源预测评价, 地质领域本体, 斑岩铜矿, 钦杭成矿带

Abstract:

Knowledge graphs, fundamental to artificial intelligence, describe the real world in graphic forms using a language that can be understood by both humans and machines. This paper presents a case study on the construction of knowledge graph for porphyry copper deposit. The raw text data were collected and integrated from six selected porphyry and porphyry-skarn copper deposits in the Qinzhou-Hangzhou Bay metallogenic belt, one of the key metallogenic belts of China. The entities, relations and attributes in the text are labeled and extracted in reference to the conceptual model of porphyry copper deposit. The resulted knowledge graph has the basic application functions. As part of a planned integrated knowledge graph—from a single deposit, through upper-geared metallogenic series, to top metallogenic province (belt)—the present study may be extended toward understanding and improving future way of mineral resource prediction and evaluation. The interrelationship among the earth system, the metallogenic system, the exploration system, and the prediction and evaluation system (ES-MS-ES-PS) should be fully understood, and a knowledge graph for the ES-MS-ES-PS system is essential. The key scientific and technological challenges to attain such a large-scale knowledge graph for the ES-MS-ES-PS system thus include system of progressive association of domain ontology and knowledge graph, automation technology for constructing large-scale domain ontology and knowledge graph, self-evolution and complementary techniques for embedding multi-modal correlation data into knowledge graph, and ES-resource prediction theory and methods based on knowledge graph, big-data mining and artificial intelligence.

Key words: knowledge graph, knowledge acquisition, geological big data, prediction and evaluation of mineral resource, geological domain ontology, porphyry copper deposit, Qinzhou-Hangzhou Bay metallogenic belt (South China)

中图分类号:

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.

ZHOU Yongzhang, ZHANG Qianlong, HUANG Yongjian, YANG Wei, XIAO Fan, JI Junjie, HAN Feng, TANG Lei, OUYANG Chong, SHEN Wenjie. Constructing knowledge graph for the porphyry copper deposit in the Qingzhou-Hangzhou Bay area: Insight into knowledge graph based mineral resource prediction and evaluation[J]. Earth Science Frontiers, 2021, 28(3): 67-75.

图/表 6

图1 知识图谱的实体、属性、关系表达示意图

Fig.1 Schematic diagram showing the entities, attributes and relations in a knowledge graph

表1 标准化后的csv格式数据(片段)

Table 1 Standardized data (partial) in csv format

节点	节点类型	关系	实体	实体类型
圆珠顶斑岩铜矿	斑岩铜矿	岩浆作用	二长花岗岩	岩浆作用类型
德兴斑岩铜矿	斑岩铜矿	变质作用	千枚岩	变质作用类型
南和斑岩铜矿	斑岩铜矿	构造作用	小王垌断裂带	构造作用类型
天堂铜多金属矿	斑岩铜矿	地层演化	天子岭组	地层类型
石菉铜矿	斑岩铜矿	围岩蚀变	硅化	围岩蚀变作用类型
岭后铜矿	斑岩铜矿	元素富集与贫化	Cu含量	元素富集与贫化类型

图2 钦杭成矿带斑岩铜矿知识图谱

Fig.2 Knowledge graph for the porphyry copper deposit in the Qinzhou-Hangzhou Bay metallogenic belt, South China

图3 与德兴铜矿有向关系的节点(不同颜色代表不同类型的地质属性)

Fig.3 Nodes having directional relations to the Dexing porphyry copper deposit(Different colors indicate different types of geological properties)

图4 浅成低温热液成矿系统知识图谱可视化界面

Fig.4 A sectional visualization of a knowledge graph for epithermal metallogenic system

图5 钦杭成矿带知识图谱可视化截面

Fig.5 A sectional visualization of the knowledge graph for the Qinzhou-Hangzhou Bay metallogenic belt

参考文献 19

[1]	张旗. 大数据助地质腾飞[J]. 岩石学报, 2018, 34(11):3167-3172.
[2]	周永章, 张良均, 张奥多, 等. 地球科学大数据挖掘与机器学习[M]. 广州: 中山大学出版社, 2018: 1-269.
[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]	AMIT S. Introducing the knowledge graph[R]. America California: Official Blog of Google, 2012.
[5]	WU W T, LI H S, WANG H X, et al. Probase: a probabilistic taxonomy for text understanding[C]// SIGMOD’12: Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data. Arizona: SIGMOD’12, 2012: 481-492.
[6]	HOFFART J, SUCHANEK F M, BERBERICH K, et al. YAGO2: a spatially and temporally enhanced knowledge base from Wikipedia[J]. Artificial Intelligence, 2013, 194:28. DOI URL
[7]	LUKOVNIKOV D, FISCHER A, LEHMANN J, et al. Neural network-based question answering over knowledge graphs on world and character level[C]. Perth, Australia: International World Wide Web Conferences Steering Committee, 2017: 1211-1220.
[8]	XU B, XU Y, LIANG J Q, et al. CN-DBpedia: a never-ending Chinese knowledge extraction system[C]. Proceedings of the 30th international conference on industrial engineering and other applications of applied intelligent systems (IEA/AIE). Arras, France:International Neural Network Society, 2017, 10351:428-438.
[9]	PALUMBO E, RIZZO G, TRONCY R, et al. An empirical comparison of knowledge graph embeddings for item recommendation[C]. Proceedings of the 14th International Conference on ICT in Education, Research and Industrial Applications. Integration, harmonization and knowledge transfer, Volume I: main conference. Kyiv, Ukraine:Kherson State University, 2018.
[10]	WANG C, YU H, WAN F. Information retrieval technology based on knowledge graph[M]//Proceedings of the 2018 3rd international conference on advances in materials, mechatronics and civil engineering (ICAMMCE 2018). Paris: Atlantis Press, 2018.
[11]	Peak Labs. About OpenKG. CN[EB/OL].Professional Committee of Language and Knowledge Computing Chinese information Processing Society of China[2020-02-28]. http://wp.openkg.cn/?page_id=77.
[12]	齐浩, 董少春, 张丽丽, 等. 地球科学知识图谱的构建与展望[J]. 高校地质学报, 2020, 26(1):2-10.
[13]	刘峤, 李杨, 段宏, 等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016, 53(3):582-600.
[14]	SAHOO S, HALB W, HELLMANN S, et al. A survey of current approaches for mapping of relational databases to RDF[R]. W3C RDB2RDF Incubator Group Report, 2009, 1:113-130.
[15]	陈悦, 陈超美, 刘则渊, 等. CiteSpace知识图谱的方法论功能[J]. 科学学研究, 2015, 33(2):242-253.
[16]	KNUBLAUCH H, FERGERSON R W, NOY N F, et al. The Protégé OWL plugin: an open development environment for semantic web applications[J]. Lecture Notes in Computer Science, 2014, 3298(1). DOI: 10.1007/978-3-540-30475-3_17. DOI
[17]	Neo Technology. Neo4j: the world’s leading graph database[EB/OL]. [2019-02-01]. http://www.neo4j.org/.
[18]	AGTERBERG F. Geomathematics: theoretical foundations, applications and future developments[M]// Quantitative geology and geostatistics. New York: Springer, 2014: 18.
[19]	赵鹏大. 成矿定量预测与深部找矿[J]. 地学前缘, 2007, 14(5):1-10.

钦杭成矿带斑岩铜矿知识图谱构建及应用展望

Constructing knowledge graph for the porphyry copper deposit in the Qingzhou-Hangzhou Bay area: Insight into knowledge graph based mineral resource prediction and evaluation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价

[1]	肖凡, 王恺其. 德兴斑岩铜矿床断裂与侵入体产状对成矿的控制作用:从力-热-流三场耦合数值模拟结果分析[J]. 地学前缘, 2021, 28(3): 190-207.
[2]	秦克章, 赵俊兴, 范宏瑞, 唐冬梅, 李光明, 余可龙, 曹明坚, 苏本勋. 试论主要类型矿床的形成深度与最大延深垂幅[J]. 地学前缘, 2021, 28(3): 271-294.
[3]	侯增谦, 杨志明, 王瑞, 郑远川. 再论中国大陆斑岩Cu-Mo-Au矿床成矿作用[J]. 地学前缘, 2020, 27(2): 20-44.
[4]	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.
[5]	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.
[6]	王堃屹，周永章，王俊，张奥多，余晓彤，焦守涛，刘心怡. 推荐系统算法在钦杭成矿带南段文地幅矿床预测中的应用[J]. 地学前缘, 2019, 26(4): 131-137.
[7]	潘彦宁，董国臣，李雪峰，王鹏. 滇西北斑岩铜矿带中黑云母矿物化学及其成岩成矿指示意义[J]. 地学前缘, 2017, 24(6): 194-207.
[8]	李文昌, 刘学龙. 云南普朗斑岩型铜矿田构造岩相成矿规律与控矿特征[J]. 地学前缘, 2015, 22(4): 53-66.
[9]	周永章, 郑义, 曾长育, 梁锦. 关于钦杭成矿带的若干认识[J]. 地学前缘, 2015, 22(2): 1-6.
[10]	徐德明, 蔺志永, 骆学全, 张鲲, 张雪辉, 黄皓. 钦杭成矿带主要金属矿床成矿系列[J]. 地学前缘, 2015, 22(2): 7-24.
[11]	劳妙姬, 邹和平, 杜晓东, 丁汝鑫. 广西横县马山晚侏罗世钾玄质侵入岩的年代学和地球化学研究：兼论钦杭成矿带西南段燕山期构造背景[J]. 地学前缘, 2015, 22(2): 95-107.
[12]	李兴远, 周永章, 安燕飞, 吕文超, 白明亮. 钦杭成矿带南段丰村铅锌矿区下园垌矿段围岩微量元素的地球化学特征及其意义[J]. 地学前缘, 2015, 22(2): 131-143.
[13]	薛春纪, 段士刚, 柴凤梅, 木合塔尔·买买提, А.Х.Туресебеков3, 屈文俊. 乌兹别克斯坦Almalyk斑岩铜矿田成矿时代及其地质意义[J]. 地学前缘, 2013, 20(2): 197-204.
[14]	薛春纪, 赵战锋, 吴淦国, 董连慧, 冯京, 张招崇, 周刚, 池国祥, 高景岗. 中亚构造域多期叠加斑岩铜矿化: 以阿尔泰东南缘哈腊苏铜矿床地质、地球化学和成岩成矿时代研究为例[J]. 地学前缘, 2010, 17(2): 53-82.
[15]	曾键年许继峰. 埃达克质岩与成矿:困惑与探索[J]. 地学前缘, 2008, 15(6): 278-292.