运用机器学习和锆石微量元素构建花岗岩成矿潜力判别图解：以东昆仑祁漫塔格为例

郭广慧; 钟世华; 李三忠; 丰成友; 戴黎明; 索艳慧; 刘嘉情; 牛警徽; 黄宇; 薛梓萌

doi:10.12401/j.nwg.2023158

运用机器学习和锆石微量元素构建花岗岩成矿潜力判别图解：以东昆仑祁漫塔格为例

郭广慧^{1, 2, 3, 4,},
钟世华^{1, 2, 3, 4, ,},
李三忠^{1, 2, 3, 4},
丰成友⁵,
戴黎明^{1, 2, 3, 4},
索艳慧^{1, 2, 3, 4},
刘嘉情^{1, 2, 3, 4},
牛警徽³,
黄宇^{1, 2, 3, 4},
薛梓萌^{1, 2, 3, 4}

1.
中国海洋大学，深海圈层与地球系统教育部前沿科学中心，山东青岛　266100
2.
中国海洋大学，海底科学与探测技术教育部重点实验室，山东青岛　266100
3.
中国海洋大学海洋地球科学学院，山东青岛　266100
4.
青岛海洋科学与技术国家实验室，海洋矿产资源评价与探测技术功能实验室，山东青岛　266100
5.
中国地质科学院勘探技术研究所，河北廊坊　065000

基金项目: 国家自然科学青年基金项目（42203066）和山东省自然科学青年基金项目（ZR2020QD027）联合资助。

详细信息

作者简介:
郭广慧（2000−），女，硕士研究生，矿物学、岩石学、矿床学专业。E−mail：guoguanghui778@163.com

通讯作者:
钟世华（1989−），男，博士，副教授，从事地质大数据与成矿研究。E−mail: zhongshihua@ouc.edu.cn

中图分类号: P62；P588.1
计量
- 文章访问数: 218
- HTML全文浏览量: 71
- PDF下载量: 182
出版历程
- 收稿日期: 2023-07-23
- 修回日期: 2023-08-31
- 录用日期: 2023-09-01
- 网络出版日期: 2023-08-08
- 刊出日期: 2023-12-19

Constructing Discrimination Diagrams for Granite Mineralization Potential by Using Machine Learning and Zircon Trace Elements: Example from the Qimantagh, East Kunlun

GUO Guanghui^{1, 2, 3, 4,},
ZHONG Shihua^{1, 2, 3, 4, ,},
LI Sanzhong^{1, 2, 3, 4},
FENG Chengyou⁵,
DAI Liming^{1, 2, 3, 4},
SUO Yanhui^{1, 2, 3, 4},
LIU Jiaqing^{1, 2, 3, 4},
NIU Jinghui³,
HUANG Yu^{1, 2, 3, 4},
XUE Zimeng^{1, 2, 3, 4}

1.
Frontiers Science Center for Deep Ocean Multispheres and Earth System, Ministry of Education, Qingdao 266100, Shandong, China
2.
Key Laboratory of Submarine Geosciences and Prospecting Techniques, Ministry of Education, Qingdao 266100, Shandong, China
3.
College of Marine Geosciences, Ocean University of China, Qingdao 266100, Shandong, China
4.
Laboratory for Marine Mineral Resources, Qingdao National Laboratory for Marine Science and Technology, Qingdao 266100, Shandong, China
5.
Institute of Exploration Techniques, CAGS, Langfang 065000, Hebei, China

摘要

摘要:
由于锆石在中酸性岩中广泛存在且成分稳定、不易受到后期热液活动的扰动，因此锆石成分可以有效记录成矿岩浆信息。其中，锆石的Ce⁴⁺/Ce³⁺、Ce/Ce^*、Eu/Eu^*和Ce/Nd值可以反映岩浆氧逸度和含水量等成矿信息，已被广泛用于花岗岩类成矿潜力评价。然而，随着研究的深入发现，这些地球化学指标并不完全具有普适性。此外，以往研究均是根据对成矿岩体的“已知认识”提出成矿潜力判别方法，但考虑到成矿过程的复杂性，许多反映岩浆成矿能力的地球化学信息可能均尚未被揭露。为此，笔者以东昆仑祁漫塔格成矿带为例，借助当前广泛应用的机器学习算法之一——支持向量机，对来自该成矿带斑岩−矽卡岩Cu−Fe−Pb−Zn多金属矿床成矿岩体和全球非成矿岩体的锆石数据开展机器学习训练，目的在于挖掘能够反映岩浆成矿能力的锆石微量元素特征，从而构建花岗岩成矿潜力判别图解。模型训练结果显示，在21个常见的锆石微量元素特征中，Gd、Dy、Yb、Y、Tm等5种元素特征对识别岩浆成矿能力最为重要。在此基础上，笔者新建立了10个二元判别图解，它们在识别成矿岩体和非成矿岩体时的准确率均接近1。研究表明，利用机器学习方法和地质大数据，可以挖掘传统研究方法难以发现的新的地球化学指标和图解，这对深入认识矿床成因、指导找矿勘查具有重要意义。
- 锆石微量元素 /
- 花岗岩 /
- 二元判别图解 /
- 机器学习 /
- 东昆仑
Abstract:
Zircon is widespread and compositionally stable in intermediate–acid magmatic rocks and is resistant to later hydrothermal activities. Therefore, its composition can more accurately record information about mineralizing magmas. Among them, zircon features (such as Ce⁴⁺/Ce³⁺, Ce/Ce^*, Eu/Eu^*, and Ce/Nd) have been widely used in evaluating the mineralization potential of granitoids, because they have been found to reflect ore−forming information, such as magmatic oxygen fugacity and water content. However, further studies have revealed that the universality of these geochemical indicators has been questioned. In addition, the proposed methods for discriminating mineralization capacity are all based on the current “limited understanding” of mineralized rocks, and considering the complexity of the mineralization process, much geochemical information reflecting the capacity of magmatic mineralization may not have been revealed yet. Therefore, in the paper, taking the Qimantagh mineralized zone of the East Kunlun as an example, and with the help of one of the most widely used machine learning algorithms today (Support Vector Machine), the authors trained machine learning on zircon data from porphyry skarn Cu−Fe−Pb−Zn mineralized rock bodies in the region and zircon data from non−mineralized rock bodies around the world, and the aim is to excavate zircon trace element signatures that reflect magmatic mineralization capacity, so as to construct a new discriminative schema for granite mineralization potential. The results of the model training show that among 21 common zircon trace element features, five element features, Gd, Dy, Yb, Y and Tm are the most important for identifying the magmatic mineralization ability; based on this, 10 binary discriminant diagrams are established in this paper, and their accuracy rates in identifying mineralized and non−mineralized rock bodies are close to 1. The present study show that the use of machine learning methods and geological big data can be used to explore the potential of granite mineralization which is difficult to study with traditional research methods. The study demonstrates that machine learning methods and geological big data can be used to mine new geochemical indicators and diagrams that are difficult to discover by traditional research methods, which is of great significance to deeply understand the genesis of mineral deposits and guide the prospecting and exploration of minerals.
- zircon trace elements /
- granite /
- binary discriminant diagrams /
- machine learning /
- East Kunlun

HTML全文

图 1 祁漫塔格地质图（据Zhong et al.，2021b修改）

图中显示了文中使用的4个矿床位置分布；哈日扎斑岩Cu矿床位于图符的右侧（N35°50′，E98°30′），未在图中显示出来

Figure 1. Geological map of Qimantagh

下载: 全尺寸图片幻灯片

图 2 文中用于训练的两种类型锆石的21种特征箱状图

Figure 2. Box illustrations of the 21 features of the two types of zircon used for training in this paper

下载: 全尺寸图片幻灯片

图 3 支持向量机模型原理图

Figure 3. Support Vector Machine model schematic

下载: 全尺寸图片幻灯片

图 4 支持向量机模型的SHAP值图

图中点表示每条数据的SHAP值，颜色代表特征的值

Figure 4. SVM method based SHAP plot

下载: 全尺寸图片幻灯片

图 5 根据锆石成分构建的成矿岩体和非成矿岩体的二元判别图解

图中决策边界由支持向量机模型确定

Figure 5. Binary discriminant diagrams solution constructed based on the Support Vector Machine method obtained by training in this paper

下载: 全尺寸图片幻灯片

图 6 祁漫塔格成矿带成矿岩体和非成矿岩体的锆石Eu/Eu*–Ce/Ce*图解

Figure 6. Zircon Eu/Eu* vs. Ce/Ce* diagram from mineralized and barren rocks from the Qimantagh metallogenic belt

下载: 全尺寸图片幻灯片

图 7 外部独立验证数据在二元判别图解上的表现（数据来源于Zhong et al.，2021b）

Figure 7. Performance of external independent validation datas on binary discriminant diagrams solutions

下载: 全尺寸图片幻灯片

表 1 文中使用的锆石微量元素数据来源统计表

Table 1 Data sources of zircon trace elements used in this study

序号	矿床/地名	矿床类型	数据量	参考文献
1	祁漫塔格虎头崖	矽卡岩Cu–Pb–Zn矿床	26	Zhong et al.，2021b
2	祁漫塔格卡尔却卡	矽卡岩Cu–Pb–Zn矿床	76
3	祁漫塔格野马泉	矽卡岩Fe矿床	173
4	祁漫塔格尕林格	矽卡岩Fe矿床	19
5	祁漫塔格牛苦头	矽卡岩Pb–Zn矿床	40
6	祁漫塔格哈日扎	斑岩Cu矿床	9
7	中国西藏	–	84	Zhao et al.，2015 Dai et al.，2015 Huang et al.，2017a Huang et al.，2017b Xie et al.，2018 Zhou et al.，2017
8	中国广东	–	77	Gao et al.，2016
9	中国新疆	–	10	Tang et al.，2017
10	中国湖南	–	96	Gao et al.，2017
11	芬兰东南部	–	14	Heinonen et al.，2017
12	中国浙江	–	35	Hu et al.，2017
13	中国云南	–	36	Zhang et al.，2022
14	加拿大拉布拉多	–	1	Vezinet et al.，2018
15	中国山东	–	22	Wang et al.，2019
16	美国阿拉斯加州	–	5	Kay et al.，2019

下载: 导出CSV

表 2 两种类型锆石的成分特征统计表（10^–6）

Table 2 The compositional characteristics of the two types of zircon compiled in this paper (10^–6)

元素	成矿岩体			非成矿岩体
元素	最大值	最小值	平均值	最大值	最小值	平均值
Ti	41919.34	0.02	129.17	801.34	0.12	17.02
La	0.10	0.01	0.02	0.06	0.09	0.04
Ce	60.09	2.12	11.61	31.20	18.20	19.31
Pr	1.16	0.01	0.10	0.08	0.06	0.15
Nd	14.04	0.13	1.58	1.43	0.90	2.55
Sm	25.14	0.25	3.29	4.24	1.04	5.36
Eu	7.44	0.02	0.76	1.05	0.16	0.95
Gd	238.00	1.37	25.70	32.65	5.51	29.39
Tb	114.74	1.93	19.27	13.49	1.91	10.30
Dy	34.61	0.63	6.75	213.23	24.38	126.92
Ho	403.30	10.47	86.96	84.36	9.02	48.02
Er	147.61	4.40	33.97	453.77	40.07	218.29
Tm	702.98	24.00	171.49	115.45	10.70	47.57
Yb	146.39	5.53	36.47	1288.35	137.62	468.36
Lu	1317.17	60.20	344.94	235.22	14.88	84.07
Y	279.95	15.21	74.70	2616.15	280.97	1429.95
Hf	13873.25	6422.50	10034.54	16386.39	6657.03	11348.72
U	2249.59	56.35	349.53	251.61	53.03	465.07
Th	1716.13	17.93	199.67	201.05	41.09	284.17
Eu/Eu^*	0.77	0.03	0.42	0.21	0.14	0.20
Ce/Ce^*	6997.36	57.52	1263.89	1589.33	608.91	864.35

下载: 导出CSV

参考文献(75)

程学旗, 靳小龙, 王元卓, 等. 大数据系统和分析技术综述[J]. 软件学报, 2014, 25: 1889-1908 doi: 10.13328/j.cnki.jos.004674

CHENG Xueqi, JIN Xiaolong, WANG yuanzhuo, et al. Survey on Big Data System and Analytic Technology[J]. Journal of Software, 2014, 25: 1889-1908. doi: 10.13328/j.cnki.jos.004674

丰成友, 李东生, 吴正寿, 等. 东昆仑祁漫塔格成矿带矿床类型、时空分布及多金属成矿作用[J]. 西北地质, 2010, 43: 10-17

FENG Chengyou, LI Dongsheng, WU Zhengshou, et al. Major Types, Time-Space Distribution and Metallogeneses of Polymetallic Deposits in the Qimantage Metallogenic Belt, Eastern Kunlun Area[J]. Northwestern Geology, 2010, 43: 10-17.

丰成友, 王松, 李国臣, 等. 青海祁漫塔格中晚三叠世花岗岩: 年代学、地球化学及成矿意义[J]. 岩石学报, 2012, 28: 665-678

FENG Chengyou, WANG Song, LI Guochen, et al. Middle to Late Triassic granitoids in the Qimantage area, Qinghai Province, China: Chronology, geochemistry and metallogenic significances[J]. Acta Petrologica Sinica, 2012, 28: 665-678.

丰成友, 王雪萍, 舒晓峰, 等. 青海祁漫塔格虎头崖铅锌多金属矿区年代学研究及地质意义[J]. 吉林大学学报(地球科学版), 2011, 41: 1806-1817

FENG Chengyou, WANG Xueping, SHU Xiaofeng, et al. Isotopic Chronology of the Hutouya Skarn Lead-Zinc Polymetallic Ore District in Qimantage Area of Qinghai Province and Its Geological Significance[J]. Journal of Jilin University( Earth Science Edition), 2011, 41: 1806-1817.

高利娥, 曾令森, 严立龙, 等. 喜马拉雅淡色花岗岩——关键金属Sn-Cs-Tl的富集机制[J]. 岩石学报, 2021, 37: 2923-2943 doi: 10.18654/1000-0569/2021.10.01

GAO Lie, ZENG Lingsen, YAN Lilong, et al. Enrichment mechanisms of Sn-Cs-Tl in the Himalaya leucogranite[J]. Acta Petrologica Sinica, 2021, 37: 2923-2943. doi: 10.18654/1000-0569/2021.10.01

高永宝. 东昆仑祁漫塔格地区中酸性侵入岩浆活动与成矿作用[D]. 西安: 长安大学, 2013

GAO Yongbao. The Intermediate-acid Intrusive Magmatism and Mineralization in Qimantag, East Kunlun Moutains[D]. Xi’an: Chang’an University, 2013

高永宝, 李文渊, 李侃, 等. 东昆仑祁漫塔格白干湖-戛勒赛矿带成岩成矿时代及钨锡成矿作用[J]. 西北地质, 2012, 45: 229-241 doi: 10.3969/j.issn.1009-6248.2012.04.021

GAO Yongbao, LI Wenyuan, LI Kan, et al. Genesis and Chronology of Baiganhu-Jialesai W-Sn Mineralization Belt, Qimantage, East Kunlun Mountain, NW China[J]. Northwestern Geology, 2012, 45: 229-241. doi: 10.3969/j.issn.1009-6248.2012.04.021

顾亚祥, 丁世飞. 支持向量机研究进展[J]. 计算机科学, 2011, 38: 14-17 doi: 10.3969/j.issn.1002-137X.2011.02.004

GU Yaxiang, DING Shifei. Advances of Support Vector Machines(SVM)[J]. Computer Science, 2011, 38: 14-17. doi: 10.3969/j.issn.1002-137X.2011.02.004

韩亚楠, 刘建伟, 罗雄麟. 连续学习研究进展[J]. 计算机研究与发展, 2022, 59: 1213-1239 doi: 10.7544/issn1000-1239.20201058

Han Yanan, Liu Jianwei, Luo Xionglin. Research Progress of Continual Learning[J]. Journal of Computer Research and Development, 2022, 59: 1213-1239. doi: 10.7544/issn1000-1239.20201058

刘鹏, 张德会, 吴鸣谦, 等. 浅谈花岗岩浆热液的形成及成矿作用[J]. 地质论评, 2020, 66: 699-719 doi: 10.16509/j.georeview.2020.03.012

LIU Peng;ZHANG Dehui;WU Mingqian, et al. Discussion on magma-hydrothermal formation and mineralization of granites[J]. Geological Review, 2020, 66: 699-719. doi: 10.16509/j.georeview.2020.03.012

毛景文, 周振华, 丰成友, 等. 初论中国三叠纪大规模成矿作用及其动力学背景[J]. 中国地质, 2012, 39: 1437-1471 doi: 10.3969/j.issn.1000-3657.2012.06.001

MAO Jingwen, ZHOU Zhenhua, FENG Chengyou, et al. A preliminary study of the Triassic large-scale mineralization in China and its geodynamic setting[J]. Geology in China, 2012, 39: 1437-1471. doi: 10.3969/j.issn.1000-3657.2012.06.001

牛警徽, 田福泉, 邱敦方, 等. 山东旧店金矿床花岗岩类锆石 U-Pb 年龄及对招平断裂带南段岩浆活动规律的约束[J]. 地质通报, 2023, 42: 813-827

NIU Jinghui, TIAN Fuquan, QIU Dunfang, et al. Zircon U-Pb age of granitoids in the Jiudian gold deposit, Shandong Province and its constraints on the magmatic activity patterns in the southern section of the Zhaoping fault[J]. Geological Bulletin of China, 2023, 42: 813-827.

申萍, 潘鸿迪. 中国还原性斑岩矿床研究进展及判别标志[J]. 岩石学报, 2020, 36: 967-994 doi: 10.18654/1000-0569/2020.04.01

SHEN Ping, PAN Hongdi. Advances and its diagnostic criteria in the study of the reduced porphyry ore deposits in China[J]. Acta Petrologica Sinica, 2020, 36: 967-994. doi: 10.18654/1000-0569/2020.04.01

田承盛, 丰成友, 李军红, 等. 青海它温查汉铁多金属矿床⁴⁰Ar-³⁹Ar年代学研究及意义[J]. 矿床地质, 2013, 32: 169-176

LI Chengsheng, FENG Chengyou, LI Junhong, et al. ⁴⁰Ar-³⁹Ar geochronology of Tawenchahan Fe-polymetallic deposit in Qimantag Mountain of Qinghai Province and its geological implications[J]. 矿床地质, 2013, 32: 169-176.

王孝磊. 花岗岩研究的若干新进展与主要科学问题[J]. 岩石学报, 2017, 33: 1445-1458

WANG Xiaolei. Some new research progresses and main scientific problems of granitic rocks[J]. Acta Petrologica Sinica, 2017, 33: 1445-1458.

王瑀, 邱昆峰, 侯照亮, 等. 石英Ti/Ge-P: 基于机器学习的矿床类型判别新图解[J]. 岩石学报, 2022, 38: 281-290 doi: 10.18654/1000-0569/2022.01.18

WANG Yu, QIU Kuneng, HOU Zhaoliang, et al. Quartz Ti/Ge-P discrimination diagram: A machine learning based approach for deposit classification[J]. Acta Petrologica Sinica, 2022, 38: 281-290. doi: 10.18654/1000-0569/2022.01.18

吴福元, 李献华, 杨进辉, 等. 花岗岩成因研究的若干问题[J]. 岩石学报, 2007, 1217-1238

WU Fuyuan, LI Xianhua, YANG Jinhui, et al. Discussions on the petrogenesis of granites[J]. Acta Petrologica Sinica, 2007, 1217-1238.

姚磊, 吕志成, 于晓飞, 等. 青海祁漫塔格地区虎头崖矿床Ⅵ矿带花岗岩的成岩时代、地球化学特征和成因[J]. 吉林大学学报(地球科学版), 2015, 45: 743-758 doi: 10.13278/j.cnki.jjuese.201503109

YAO Lei, LV Zhicheng, YU Xiaofei, et al. Petrogenesis, Geochemistry and Zircon U-Pb Age of the Granite from No. Ⅵ Section of Hutouya Deposit, Qimantag Area, Qinghai Province, and Its Geological Significance[J]. Journal of Jilin University( Earth Science Edition), 2015, 45: 743-758. doi: 10.13278/j.cnki.jjuese.201503109

于淼, 丰成友, 刘洪川, 等. 青海尕林格矽卡岩型铁矿金云母40Ar-39Ar年代学及成矿地质意义[J]. 地质学报, 2015, 89: 510-521

YU Miao, FENG Chengyou, LIU Hongchuan, et al. ⁴⁰Ar-³⁹Ar Geochronology of the Galinge Large Skarn Iron Deposit in Qinghai Province and Geological Significance[J]. Acta Geologica Sinica, 2015, 89: 510-521.

张晓飞, 李智明, 陈博, 等. 东昆仑祁漫塔格地区滩间山群矽卡岩化成矿作用. [J]. 西北地质, 2012, 45: 40-47 doi: 10.3969/j.issn.1009-6248.2012.01.006

ZHANG Xiaofei, LI Zhiming, CHEN Bo, et al. The Contribution of the Tanjianshan Group Stratum to Skarnization in Qimantage Region, Qinghai Province[J]. Northwestern Geology, 2012, 45: 40-47. doi: 10.3969/j.issn.1009-6248.2012.01.006

钟世华. 新疆维宝铜铅锌矿床成因研究[D]. 北京: 中国地质科学院, 2018

ZHONG Shihua. Genesis of the Weibao Cu-Pb-Zn deposit in Xinjiang, China[D]. Beijing: Chinese Academy of Geological Sciences, 2018

钟世华, 丰成友, 李大新, 等. 新疆维宝矽卡岩铜铅锌矿床维西矿段矿物学特征[J]. 地质学报, 2017a, 91: 1066-1082

ZHONG Shihua, FENG Chengyou, LI Daxin, et al. Mineralogical Characteristics of the Weixi Ore Block in the Weibao Skarn-type Copper-Lead-Zinc Deposit, Xinjiang[J]. Acta Geologica Sinica, 2017a, 91: 1066-1082.

钟世华, 丰成友, 李大新, 等. 新疆维宝多金属矿区辉绿岩脉SIMS年代学和地球化学[J]. 地质学报, 2017b, 91: 762-775

ZHONG Shihua, FENG Chengyou, LI Daxin, et al. SIMS Chronology and Geochemistry of Diabase Dykes from the Weibao Polymetallic Orefield, Xinjiang[J]. Acta Geologica Sinica, 2017b, 91: 762-775.

钟世华, 丰成友, 任雅琼, 等. 新疆维宝矽卡岩铜铅锌矿床维西矿段成矿流体性质和来源[J]. 矿床地质, 2017c, 36: 483-500 doi: 10.16111/j.0258-7106.2017.02.014

ZHONG Shihua, FENG Chengyou, REN Yaqiong, et al. Characteristics and sources of ore-forming fluid from Weixi ore block of Weibao skarn Cu-Pb-Zn deposit, Xinjiang[J]. Mineral Deposits, 2017c, 36: 483-500. doi: 10.16111/j.0258-7106.2017.02.014

BALLARD J R, PALIN M J, CAMPBELL I H. Relative oxidation states of magmas inferred from Ce(IV)/Ce(III) in zircon: application to porphyry copper deposits of northern Chile[J]. Contributions to Mineralogy and Petrology, 2002, 144: 347-364. doi: 10.1007/s00410-002-0402-5

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: eaau0323. doi: 10.1126/science.aau0323

CAO M, QIN K, LI G, et al. Baogutu: An example of reduced porphyry Cu deposit in western Junggar[J]. Ore Geology Reviews, 2014, 56: 159-180. doi: 10.1016/j.oregeorev.2013.08.014

CHAPPELL B, WHITE A. Two contrasting granite types[J]. Pacific geology, 1974, 8: 173-174.

Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321−357.

CHELLE-MICHOU C, CHIARADIA M, OVTCHAROVA M, et al. Zircon petrochronology reveals the temporal link between porphyry systems and the magmatic evolution of their hidden plutonic roots (the Eocene Coroccohuayco deposit, Peru)[J]. Lithos, 2014, 198-199.

CHIARADIA M. How Much Water in Basaltic Melts Parental to Porphyry Copper Deposits?[J]. Frontiers in Earth Science, 2020, 8: 138. doi: 10.3389/feart.2020.00138

CORTES C, VAPNIK V. Support-vector networks[J]. Machine learning, 1995, 20: 273-297.

DAI J, WANG C, ZHU D, et al. Multi-stage volcanic activities and geodynamic evolution of the Lhasa terrane during the Cretaceous: Insights from the Xigaze forearc basin[J]. Lithos, 2015, 218: 127-140.

DEMPSTER T J, JOLIVET M, TUBRETT M N, et al. Magmatic zoning in apatite: a monitor of porosity and permeability change in granites[J]. Contributions to Mineralogy and Petrology, 2003, 145: 568-577. doi: 10.1007/s00410-003-0471-0

DILLES J H, KENT A J R, WOODEN J L, et al. Zircon compositional evidence for sulfur-degassing from ore-forming arc magmas. [J]. Economic geology and the bulletin of the Society of Economic Geologists, 2015, 110: 241-251. doi: 10.2113/econgeo.110.1.241

DU J, AUDéTAT A. Early sulfide saturation is not detrimental to porphyry Cu-Au formation[J]. Geology, 2020, 48: 519-524.

GAO P, ZHENG Y-F, ZHAO Z-F. Distinction between S-type and peraluminous I-type granites: Zircon versus whole-rock geochemistry[J]. Lithos, 2016, 258: 77-91.

GAO P, ZHENG Y-F, ZHAO Z-F. Triassic granites in South China: A geochemical perspective on their characteristics, petrogenesis, and tectonic significance[J]. Earth-Science Reviews, 2017, 173: 266-294. doi: 10.1016/j.earscirev.2017.07.016

GRIMES C B, WOODEN J L, CHEADLE M J, et al. “Fingerprinting” tectono-magmatic provenance using trace elements in igneous zircon[J]. Contributions to Mineralogy and Petrology, 2015, 170: 1-26. doi: 10.1007/s00410-015-1154-3

HANCHAR J M, WESTRENEN W V. Rare Earth Element Behavior in Zircon-Melt Systems[J]. Elements, 2007, 3: 37-42. doi: 10.2113/gselements.3.1.37

HEINONEN A P, R M O T, M NTT RI I, et al. Zircon as a proxy for the magmatic evolution of Proterozoic ferroan granites; the Wiborg rapakivi granite batholith, SE Finland[J]. Journal of Petrology, 2017, 58: 2493-2517. doi: 10.1093/petrology/egy014

Hu Q, Yu K, Liu Y, et al. The 131–134 Ma A-type granites from northern Zhejiang Province, South China: Implications for partial melting of the Neoproterozoic lower crust[J]. Lithos, 2017, 294: 39−52.

HUANG C, ZHAO Z, LI G, et al. Leucogranites in Lhozag, southern Tibet: Implications for the tectonic evolution of the eastern Himalaya[J]. Lithos, 2017a, 294: 246-262.

HUANG X, DENG J, WANG W, et al. Impact of climate and elevation on snow cover using integrated remote sensing snow products in Tibetan Plateau[J]. Remote Sensing of Environment, 2017b, 190: 274-288. doi: 10.1016/j.rse.2016.12.028

KAY S M, JICHA B R, CITRON G L, et al. The calc-alkaline Hidden Bay and Kagalaska plutons and the construction of the central Aleutian oceanic arc crust[J]. Journal of Petrology, 2019, 60: 393-439. doi: 10.1093/petrology/egy119

LEE C-T A, TANG M. How to make porphyry copper deposits[J]. Earth and Planetary Science Letters, 2020, 529: 115868. doi: 10.1016/j.jpgl.2019.115868

LIU Y, LI W, JIA Q, et al. The Dynamic Sulfide Saturation Process and a Possible Slab Break-off Model for the Giant Xiarihamu Magmatic Nickel Ore Deposit in the East Kunlun Orogenic Belt, Northern Qinghai-Tibet Plateau, China[J]. Economic Geology, 2018, 113: 1383-1417. doi: 10.5382/econgeo.2018.4596

LOADER M A, WILKINSON J J, ARMSTRONG R N. The effect of titanite crystallisation on Eu and Ce anomalies in zircon and its implications for the assessment of porphyry Cu deposit fertility[J]. Earth and Planetary Science Letters, 2017, 472: 107-119 . doi: 10.1016/j.jpgl.2017.05.010

MASSIMO C, LUCA C. Supergiant porphyry copper deposits are failed large eruptions[J]. Communications Earth & Environment, 2022, 3: 107.

NATHWANI C L, WILKINSON J J, FRY G, et al. Machine learning for geochemical exploration: classifying metallogenic fertility in arc magmas and insights into porphyry copper deposit formation[J]. Mineralium Deposita, 2022, 57: 1143-1166. doi: 10.1007/s00126-021-01086-9

PETRELLI M, CARICCHI L, PERUGINI D. Machine Learning Thermo‐Barometry: Application to Clinopyroxene‐Bearing Magmas[J]. Journal of Geophysical Research: Solid Earth, 2020, 125: e2020JB020130.

PETRELLI M, PERUGINI D. Solving petrological problems through machine learning: the study case of tectonic discrimination using geochemical and isotopic data[J]. Contributions to Mineralogy and Petrology, 2016, 171: 1-15. doi: 10.1007/s00410-015-1217-5

PIZARRO H, CAMPOS E, BOUZARI F, et al. Porphyry indicator zircons (PIZs): Application to exploration of porphyry copper deposits[J]. Ore Geology Reviews, 2020, 126: 103771. doi: 10.1016/j.oregeorev.2020.103771

RICHARDS J P, SENGOR A M C L. Did Paleo-Tethyan anoxia kill arc magma fertility for porphyry copper formation?[J]. Geology, 2017, 45: 7.

SHUMLYANSKYY L, BELOUSOVA E, PETRENKO O. Geochemistry of zircons from basic rocks of the Korosten anorthosite-mangerite-charnockite-granite complex, north-western region of the Ukrainian Shield[J]. Mineralogy and Petrology, 2017, 111: 459-466. doi: 10.1007/s00710-017-0514-2

TANG G-J, CHUNG S-L, HAWKESWORTH C J, et al. Short episodes of crust generation during protracted accretionary processes: Evidence from Central Asian Orogenic Belt, NW China[J]. Earth and Planetary Science Letters, 2017, 464: 142-154. doi: 10.1016/j.jpgl.2017.02.022

VEZINET A, PEARSON D G, THOMASSOT E, et al. Hydrothermally-altered mafic crust as source for early Earth TTG: Pb/Hf/O isotope and trace element evidence in zircon from TTG of the Eoarchean Saglek Block, N. Labrador[J]. Earth and Planetary Science Letters, 2018, 503: 95-107. doi: 10.1016/j.jpgl.2018.09.015

WADE C, PAYNE J, BAROVICH K, et al. Zircon trace element geochemistry as an indicator of magma fertility in iron oxide copper-gold provinces[J]. Economic Geology, 2022, 117: 703-718. doi: 10.5382/econgeo.4886

WANG S, LI X, SCHERTL H-P, et al. Petrogenesis of early cretaceous andesite dykes in the Sulu orogenic belt, eastern China[J]. Mineralogy and Petrology, 2019, 113: 77-97. doi: 10.1007/s00710-018-0636-1

XIA R, WANG C, QING M, et al. Molybdenite Re–Os, zircon U–Pb dating and Hf isotopic analysis of the Shuangqing Fe–Pb–Zn–Cu skarn deposit, East Kunlun Mountains, Qinghai Province, China[J]. Ore Geology Reviews, 2015, 66: 114-131. doi: 10.1016/j.oregeorev.2014.10.024

XIE F, TANG J, LANG X, et al. The different sources and petrogenesis of Jurassic intrusive rocks in the southern Lhasa subterrane, Tibet: Evidence from the trace element compositions of zircon, apatite, and titanite[J]. Lithos, 2018, 314: 447-462.

YU M, DICK J M, FENG C, et al. The tectonic evolution of the East Kunlun Orogen, northern Tibetan Plateau: A critical review with an integrated geodynamic model[J]. Journal of Asian Earth Sciences, 2020, 191: 104168. doi: 10.1016/j.jseaes.2019.104168

ZHANG Q, WANG Q, LI G, et al. Crucial control on magmatic-hydrothermal Sn deposit in the Tengchong block, SW China: Evidence from magma differentiation and zircon geochemistry[J]. Geoscience Frontiers, 2022, 13: 101401. doi: 10.1016/j.gsf.2022.101401

ZHAO S-Q, TAN J, WEI J-H, et al. Late Triassic Batang Group arc volcanic rocks in the northeastern margin of Qiangtang terrane, northern Tibet: partial melting of juvenile crust and implications for Paleo-Tethys ocean subduction[J]. International Journal of Earth Sciences, 2015, 104: 369-387. doi: 10.1007/s00531-014-1080-z

ZHONG S, FENG C, SELTMANN R, et al. Sources of fluids and metals and evolution models of skarn deposits in the Qimantagh metallogenic belt: A case study from the Weibao deposit, East Kunlun Mountains, northern Tibetan Plateau[J]. Ore Geology Reviews, 2018a, 93: 19-37. doi: 10.1016/j.oregeorev.2017.12.013

ZHONG S, FENG C, SELTMANN R, et al. Geochemical contrasts between Late Triassic ore-bearing and barren intrusions in the Weibao Cu–Pb–Zn deposit, East Kunlun Mountains, NW China: constraints from accessory minerals (zircon and apatite)[J]. Mineralium Deposita, 2018b, 53: 855-870. doi: 10.1007/s00126-017-0787-8

ZHONG S, LI S, FENG C, et al. Geochronology and geochemistry of mineralized and barren intrusive rocks in the Yemaquan polymetallic skarn deposit, northern Qinghai-Tibet Plateau: A zircon perspective[J]. Ore Geology Reviews, 2021b, 139: 104560. doi: 10.1016/j.oregeorev.2021.104560

ZHONG S, LI S, FENG C, et al. Porphyry copper and skarn fertility of the northern Qinghai-Tibet Plateau collisional granitoids[J]. Earth-Science Reviews, 2021c, 214: 103524. doi: 10.1016/j.earscirev.2021.103524

ZHONG S, LI S, LIU Y, et al. I-type and S-type granites in the Earth’s earliest continental crust[J]. Communications Earth & Environment, 2023, 4: 61.

ZHONG S, SELTMANN R, QU H, et al. Characterization of the zircon Ce anomaly for estimation of oxidation state of magmas: a revised Ce/Ce* method[J]. Mineralogy and Petrology, 2019, 113: 755-763. doi: 10.1007/s00710-019-00682-y

ZHONG S H, FENG C, SELTMANN R, et al. Middle Devonian volcanic rocks in the Weibao Cu–Pb–Zn deposit, East Kunlun Mountains, NW China: Zircon chronology and tectonic implications[J]. Ore Geology Reviews, 2017, 84: 309-327. doi: 10.1016/j.oregeorev.2017.01.020

H. ZS, Y. L, Z. L S, et al. A machine learning method for distinguishing detrital zircon provenance[J]. Contributions to Mineralogy and Petrology, 2023, 178: 35. doi: 10.1007/s00410-023-02017-9

ZHOU G, WU Y, WANG H, et al. Petrogenesis of the Huashanguan A-type granite complex and its implications for the early evolution of the Yangtze Block[J]. Precambrian Research, 2017, 292: 57-74. doi: 10.1016/j.precamres.2017.02.005

ZHU J-J, HU R, BI X-W, et al. Porphyry Cu fertility of eastern Paleo-Tethyan arc magmas: Evidence from zircon and apatite compositions[J]. Lithos, 2022, 424: 106775.

ZOU S, CHEN X, BRZOZOWSKI M J, et al. Application of machine learning to characterizing magma fertility in porphyry Cu deposits[J]. Journal of Geophysical Research: Solid Earth, 2022, 127: e2022JB024584. doi: 10.1029/2022JB024584

施引文献

资源附件(0)

图(7) / 表(2)

计量

文章访问数: 218
HTML全文浏览量: 71
PDF下载量: 182
被引次数: 0

运用机器学习和锆石微量元素构建花岗岩成矿潜力判别图解：以东昆仑祁漫塔格为例

作者简介: 郭广慧（2000−），女，硕士研究生，矿物学、岩石学、矿床学专业。E−mail：guoguanghui778@163.com

通讯作者: 钟世华（1989−），男，博士，副教授，从事地质大数据与成矿研究。E−mail: zhongshihua@ouc.edu.cn

计量

出版历程

Constructing Discrimination Diagrams for Granite Mineralization Potential by Using Machine Learning and Zircon Trace Elements: Example from the Qimantagh, East Kunlun

计量

出版历程

目录

作者简介:
郭广慧（2000−），女，硕士研究生，矿物学、岩石学、矿床学专业。E−mail：guoguanghui778@163.com

通讯作者:
钟世华（1989−），男，博士，副教授，从事地质大数据与成矿研究。E−mail: zhongshihua@ouc.edu.cn