老挝铜资源成矿规律与基于机器学习的远景预测

doi:10.13745/j.esf.sf.2024.10.43

地学前缘 ›› 2025, Vol. 32 ›› Issue (1): 61-77.DOI: 10.13745/j.esf.sf.2024.10.43

• 特提斯成矿带战略资源地球化学调查评价 • 上一篇下一篇

老挝铜资源成矿规律与基于机器学习的远景预测

张必敏¹^,²(), 王学求¹^,², 周建¹^,²^,^*(), 王玮¹^,²^,^*(), 刘汉粮¹^,², 刘东盛¹^,², Sounthone LAOLO³, Phomsylalai SOUKSAN³, 谢淼¹^,², 董春放¹^,², 柳青青¹^,², 鲁岳鑫¹^,², 王浩楠¹^,²^,⁴, 贺彬¹^,²^,⁵

1.自然资源部地球化学探测重点实验室, 自然资源部深地科学与探测技术实验室, 中国地质科学院地球物理地球化学勘查研究所, 河北廊坊 065000
2.联合国教科文组织全球尺度地球化学国际研究中心, 河北廊坊 065000
3.老挝人民民主共和国能源与矿产部地矿司, 老挝万象 01000
4.桂林理工大学, 广西桂林 541004
5.中国地质大学(北京), 北京 100083

收稿日期:2024-08-01 修回日期:2024-10-12 出版日期:2025-01-25 发布日期:2025-01-15
通信作者: *周建(1982—),男,高级工程师,主要从事勘查地球化学研究。E-mail: zhoujian@mail.cgs.gov.cn;王玮(1984—),女,高级工程师,主要从事勘查地球化学研究。E-mail: wangwei@mail.cgs.gov.cn
作者简介:张必敏(1981—),男,研究员,主要从事勘查地球化学与全球地球基准研究。E-mail: zbimin@hotmail.com
基金资助:
中国地质调查局地质调查项目(DD20221807);中国地质调查局地质调查项目(DD20190451)

Copper mineralization pattern and machine learning-based copper prospectivity prediction in Laos

ZHANG Bimin¹^,²(), WANG Xueqiu¹^,², ZHOU Jian¹^,²^,^*(), WANG Wei¹^,²^,^*(), LIU Hanliang¹^,², LIU Dongsheng¹^,², Sounthone LAOLO³, Phomsylalai SOUKSAN³, XIE Miao¹^,², DONG Chunfang¹^,², LIU Qingqing¹^,², LU Yuexin¹^,², WANG Haonan¹^,²^,⁴, HE Bin¹^,²^,⁵

1. Ministry of Natural Resources Key Laboratory of Geochemical Exploration, Ministry of Natural Resources SinoProbe Laboratory, Institute of Geophysical and Geochemical Exploration, Chinese Academy of Geological Sciences, Langfang 065000, China
2. UNESCO International Centre on Global-scale Geochemistry, Langfang 065000, China
3. Department of Geology and Minerals, Ministry of Energy and Mines,Vientiane 01000, Laos
4. Guilin University of Technology, Guilin 541004, China
5. School of Earth and Resources, China University of Geosciences (Beijing), Beijing 100083, China

Received:2024-08-01 Revised:2024-10-12 Online:2025-01-25 Published:2025-01-15

摘要/Abstract

摘要：

老挝处于特提斯成矿域南东段,具有丰富的矿产资源,但其地质工作基础薄弱,厘定矿产资源成矿规律并开展远景区预测是老挝在重点区实现找矿突破的有效途径。老挝1∶1 000 000国家尺度地球化学填图由中老双方合作完成,为其矿产资源和环境评价提供了高质量的地球化学基础数据和图件。本文主要利用国家尺度地球化学填图数据,结合老挝已发现矿产成矿规律,利用机器学习技术,开展铜资源远景区预测。研究结果表明:(1)老挝铜矿床的形成明显受到构造-岩浆-沉积作用控制,铜矿床主要类型有斑岩型、夕卡岩型、热液型和砂岩型。(2)老挝全国水系沉积物中铜含量为1.20~459.00 μg/g,平均值为21.96 μg/g,中位值为16.50 μg/g,在7个三级大地构造单元中,长山地块和哀牢山—马江等3个缝合带的平均值高于其他几个构造单元,地球化学图显示铜在老挝分布不均匀,存在多个大面积分布的高背景区和异常区。(3)构建了包括单元素异常、矿化元素组合异常、指示中酸性岩体元素组合、控矿构造分布、碳酸盐岩和碎屑岩分布等要素的老挝铜矿多源信息定量信息预测模型。(4)利用随机森林成矿预测方法,共圈定9个成矿远景区,具有寻找斑岩型和夕卡岩型等类型铜矿找矿前景。

关键词: 远景区预测, 机器学习, 铜成矿规律, 地球化学填图, 老挝

Abstract:

Laos is located in the southeastern segment of the Tethyan metallogenic domain, in the southern extension of the Sanjiang metallogenic belt. It has abundant mineral resources but is lacking high-level geological research. Metallogenic and mineral prospectivity modeling, therefore, is an effective way to achieving major breakthroughs in mineral exploration in Laos. The 1∶1000000 national-scale geochemical mapping project in Laos has provided high-quality geochemical baseline data and maps for mineral resource and environmental evaluation. This paper utilizes data obtained from the mapping project, combined with the metallogenic pattern of known minerals in Laos, and applies machine learning techniques to predict propective copper resource areas. The results show that (1) the formation of copper deposits in Laos is significantly controlled by tectonic-magmatic-sedimentary processes. The main types of copper deposits are porphyry, skarn, hydrothermal, and sandstone. (2) The copper content in stream sediments of Laos ranged between 1.20-459 μg/g, with an average value of 21.96 μg/g and a median value of 16.50 μg/g. Among the seven tertiary tectonic units, the average copper content was higher in the Changshan block and three suture zones than in other tectonic units. Geochemical maps reveal uneven distribution of copper, with occurrence of several large, high background and anomaly areas. (3) A quantitative, multisource information prediction model for copper deposits in Laos was constructed, with model factors such as single-element anomalies, multielement combination anomalies, multielement combinations indicative of acidic rocks, the distribution of ore-controlling structures, and the distribution of carbonate and clastic rocks. (4) Using the Random Forest metallogenic prediction method, nine metallogenic prospective areas were delineated, which have great prospecting potential for various types of copper deposits, such as porphyry and skarn.

Key words: prospecting area prediction, machine learning, copper mineralization patterns, geochemical mapping, Laos

中图分类号:

P595
P596

张必敏, 王学求, 周建, 王玮, 刘汉粮, 刘东盛, Sounthone LAOLO, Phomsylalai SOUKSAN, 谢淼, 董春放, 柳青青, 鲁岳鑫, 王浩楠, 贺彬. 老挝铜资源成矿规律与基于机器学习的远景预测[J]. 地学前缘, 2025, 32(1): 61-77.

ZHANG Bimin, WANG Xueqiu, ZHOU Jian, WANG Wei, LIU Hanliang, LIU Dongsheng, Sounthone LAOLO, Phomsylalai SOUKSAN, XIE Miao, DONG Chunfang, LIU Qingqing, LU Yuexin, WANG Haonan, HE Bin. Copper mineralization pattern and machine learning-based copper prospectivity prediction in Laos[J]. Earth Science Frontiers, 2025, 32(1): 61-77.

图/表 15

图1 老挝及邻区区域构造略图(a)和地质构造简图(b)(据文献[2,5,27]修改)

Fig.1 Simplified regional structural map (a) and geological sketch map and structural units of Laos (b). Modified from [2,5,27].

图2 富开铜金矿区地质图(据文献[68]) 1—呵叻盆地红层;2—沉积杂岩;3—灰岩;4—花岗岩;5—砾岩;6—粉砂岩;7—红层;8—斑岩脉;9—细粒花岗岩脉;10—断层;11—逆断层;12—河流。

Fig.2 Geological map of the Phu Khan Cu-Au deposit. Adapted from [68].

图3 色奔斑岩型铜金矿矿区地质图(据文献[74])

Fig.3 Geological map of the Seben porphyry Cu-Au deposit. Adapted from [74].

图4 班康姆铜金矿床地质图(据文献[78]) 1—石炭系—二叠系灰岩;2—二叠系夕卡岩化大理岩;3—石炭系—二叠系泥质砂岩;4—安山质凝灰岩;5—花岗闪长岩;6—安山岩;7—铜金矿体和编号;8—断层和编号。

Fig.4 Geological sketch map of the Pangkuam Cu-Au deposit. Adapted from [78].

表1 老挝铜矿主要成矿要素

Table 1 Main metallogenic controlling factors of copper deposits in Laos

成矿要素	描述模式
大地构造位置	长山火山弧带、奠边府—黎府缝合带和兰坪—思茅盆地
主要赋矿层位	花岗闪长斑岩及斑岩体与围岩接触带、中-酸性火山岩和砂岩
控矿沉积建造	二叠系陆相-浅海相碎屑沉积和碳酸盐岩和白垩系陆源碎屑沉积
控矿侵入岩	古生代—早中生代酸性侵入岩、中性闪长玢岩和花岗闪长斑岩
成矿类型	斑岩型、夕卡岩型、热液型和砂岩型
控矿构造	区域性南北向、北东向和北西向断裂
主成矿期	晚石炭世—早三叠世和侏罗世—早白垩世

表2 老挝铜元素地球化学参数统计表

Table 2 Statistical of Cu geochemical parameters in Laos

统计单元	统计参数
统计单元	样品数/件	最小值/ (μg·g^-1)	平均值/ (μg·g^-1)	中位值/ (μg·g^-1)	最大值/ (μg·g^-1)	标准差/ (μg·g^-1)
老挝全境	1 905	1.20	21.96	16.50	459.00	26.06
景洪—素可泰火山弧带	112	4.21	18.63	17.54	50.56	7.76
思茅—彭世洛地块	504	1.29	22.62	17.04	393.70	24.53
奠边府—黎府缝合带	44	8.31	23.77	19.72	72.40	15.72
万象—昆嵩地块	665	1.20	19.82	12.20	459.00	31.03
色潘—三岐缝合带	22	3.40	23.61	18.40	92.30	19.63
长山地块	549	2.47	23.78	19.13	328.50	24.34
哀牢山—马江缝合带	9	3.65	25.53	18.18	82.76	24.84

老挝铜资源成矿规律与基于机器学习的远景预测

Copper mineralization pattern and machine learning-based copper prospectivity prediction in Laos

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 15