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

doi:10.13745/j.esf.sf.2024.10.43

Abstract

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

CLC Number:

P595
P596

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.

Figures/Tables 15

References 95

[1]	ZAW K, MEFFRE S, LAI C K, et al. Tectonics and metallogeny of mainland Southeast Asia: a review and contribution[J]. Gondwana Research, 2014, 26(1): 5-30.
[2]	王宏, 林方成, 李兴振, 等. 老挝及邻区构造单元划分与构造演化[J]. 中国地质, 2015, 42(1): 71-84.
[3]	陈喜峰, 陈秀法, 叶锦华, 等. 东南亚矿产资源概论[M]. 北京: 地质出版社, 2020.
[4]	卢映祥, 刘洪光, 黄静宁, 等. 东南亚中南半岛成矿带初步划分与区域成矿特征[J]. 地质通报, 2009, 28(增刊1): 314-325.
[5]	贾润幸, 方维萱, 隗雪燕. 老挝地质矿产资源及开发概况[J]. 矿产勘查, 2014, 5(5): 826-833.
[6]	贾若, 徐巧, 张鹤, 等. 老挝矿产资源成矿规律与找矿潜力分析[J]. 世界有色金属, 2023(12): 60-62.
[7]	杨卓龙, 王利, 邢佳韵, 等. 老挝矿业投资现状及投资建议[J]. 中国矿业, 2017, 26(11): 70-73.
[8]	马树洪. 老挝的矿业开发及其国际合作[J]. 东南亚南亚研究, 2009(3): 51-55, 93.
[9]	程新, 沈镭, 高天明. 中南半岛五国矿产资源开发现状及中国的投资取向[J]. 资源科学, 2011, 33(10): 1847-1854.
[10]	张念. 老挝矿产资源概况及中老矿业合作开发前景[J]. 铜业工程, 2015(4): 85-93.
[11]	WANG X Q, ZHANG B M, NIE L S, et al. Mapping chemical earth program: progress and challenge[J]. Journal of Geochemical Exploration, 2020, 217: 106578.
[12]	王玮, 王学求, 张必敏, 等. 老挝全国地球化学填图与成矿远景区预测[J]. 地球学报, 2020, 41(1): 80-90.
[13]	王玮, 王学求, 张必敏, 等. 老挝表层沉积物69种元素地球化学背景值[J]. 地球科学, 2022, 47(8): 2765-2780.
[14]	王学求, 迟清华, 孙宏伟. 荒漠戈壁区超低密度地球化学调查与评价: 以东天山为例[J]. 新疆地质, 2001, 19(3): 200-206.
[15]	王学求, 刘汉粮, 王玮, 等. 中国锂矿地球化学背景与空间分布: 远景区预测[J]. 地球学报, 2020, 41(6): 797-806.
[16]	谢学锦. 战术性与战略性的深穿透地球化学方法[J]. 地学前缘, 1998, 5(2): 2-14.
[17]	王学求, 谢学锦, 张本仁, 等. 地壳全元素探测: 构建“化学地球”[J]. 地质学报, 2010, 84(6): 854-864.
[18]	XIE X J, MU X Z, REN T X. Geochemical mapping in China[J]. Journal of Geochemical Exploration, 1997, 60(1): 99-113.
[19]	谢学锦. 全球地球化学填图: 历史发展与今后工作之建议[J]. 中国地质, 2008, 35(3): 357-374.
[20]	师洪涛, 严城民, 苏俊, 等. 老挝构造单元分界断裂位置与特征[J]. 云南地质, 2023, 42(4): 417-421.
[21]	GUO L N, DENG J, HOU L, et al. Gold source and deposition in the sanakham gold deposit, SW Laos: constrains from textures, trace element geochemistry and in situ sulfur isotopes of pyrite[J]. Ore Geology Reviews, 2024, 167: 106003.
[22]	赵延朋, 何国朝, 陆家海. 老挝典型金矿床地质特征及成矿模式[J]. 矿产与地质, 2013, 27(增刊1): 41-46.
[23]	施美凤, 林方成, 刘朝基, 等. 东南亚缅泰老越柬五国与中国邻区成矿带划分及成矿特征[J]. 沉积与特提斯地质, 2013, 33(2): 103-112.
[24]	SHI M F, ZAW K, LIU SS, et al. Geochronology and petrogenesis of Carboniferous and Triassic volcanic rocks in NW Laos: implications for the tectonic evolution of the Loei fold belt[J]. Journal of Asian Earth Sciences, 2021, 208: 104661.
[25]	陈喜峰. 东南亚中南半岛大地构造单元划分研究现状与存在问题[J]. 矿物学报, 2015, 35(增刊1): 1071-1072.
[26]	莫宣学, 邓晋福, 董方浏, 等. 西南三江造山带火山岩-构造组合及其意义[J]. 高校地质学报, 2001, 7(2): 121-138.
[27]	SHI M F, LIN F C, FAN W Y, et al. Zircon U-Pb ages and geochemistry of granitoids in the Truong Son terrane, Vietnam: tectonic and metallogenic implications[J]. Journal of Asian Earth Sciences, 2015, 101: 101-120.
[28]	陈喜峰, 向运川, 叶锦华, 等. 东南亚中南半岛锡矿带成矿特征[J]. 地质通报, 2015, 34(4): 734-745.
[29]	吴良士. 老挝人民民主共和国矿产资源及其地质特征[J]. 矿床地质, 2009, 28(2): 224-226.
[30]	陈喜峰, 叶锦华, 向运川, 等. 东南亚地区重要矿床地质特征及找矿潜力[J]. 地质通报, 2017, 36(1): 50-65.
[31]	朱延浙, 吴军, 崔子良, 等. 老挝北部地区矿产资源与成矿预测[J]. 矿产与地质, 2007, 21(6): 665-667.
[32]	SHEN L J, SIRITONGKHAM N. The characteristics, formation and exploration progress of the potash deposits on the Khorat Plateau, Thailand and Laos, Southeast Asia[J]. China Geology, 2020, 3(1): 67-82.
[33]	LIU W L, WANG G W, CHEN Y Q, et al. The structural information and alteration information extraction and metallogenic prognosis in Laos area[J]. Procedia Environmental Sciences, 2011, 10: 386-391.
[34]	SANEMATSU K, MURAKAMI H, WATANABE Y, et al. Enrichment of rare earth elements (REE) in graniticrocks and their weathered crusts in central and southern Laos[J]. Bulletin of the Geological Survey of Japan, 2009, 60(11/12): 527-558.
[35]	吕亮, 王思德, 俎波, 等. 老挝稀土资源特征及勘查开发前景[J]. 地质科技通报, 2022, 41(3): 20-31.
[36]	胡雄伟, 吴良士. 老挝人民民主共和国地质特征与区域成矿[J]. 矿床地质, 2009, 28(1): 104-106.
[37]	王宏, 林方成, 施美凤. 老挝及邻区主要矿产成矿规律[J]. 矿床地质, 2012, 31(增刊1): 1177-1178.
[38]	ZOU H J, HAN R S, LIU M Q, et al. Geological, geophysical, and geochemical characteristics of the Ban Kiouchep Cu-Pb-Ag deposit and its exploration significance in Northern Laos[J]. Ore Geology Reviews, 2020, 124: 103603.
[39]	CARRANZA E J M. Controls on mineral deposit occurrence inferred from analysis of their spatial pattern and spatial association with geological features[J]. Ore Geology Reviews, 2009, 35(3/4): 383-400.
[40]	CARRANZA E J M. Natural resources research publications on geochemical anomaly and mineral potential mapping, and introduction to the special issue of papers in these fields[J]. Natural Resources Research, 2017, 26(4): 379-410.
[41]	LIU Y, CARRANZA E J M, XIA Q L. Developments in quantitative assessment and modeling of mineral resource potential: an overview[J]. Natural Resources Research, 2022, 31(4): 1825-1840.
[42]	WANG J, ZUO R G, XIONG Y H. Mapping mineral prospectivity via semi-supervised random forest[J]. Natural Resources Research, 2020, 29(1): 189-202.
[43]	成秋明. 什么是数学地球科学及其前沿领域?[J]. 地学前缘, 2021, 28(3): 6-25. DOI
[44]	XIONG Y H, ZUO R G. GIS-based rare events logistic regression for mineral prospectivity mapping[J]. Computers & Geosciences, 2018, 111: 18-25.
[45]	XIAO F, WANG K Q, HOU W S, et al. Prospectivity mapping for porphyry Cu-Mo mineralization in the Eastern Tianshan, Xinjiang, Northwestern China[J]. Natural Resources Research, 2020, 29(1): 89-113.
[46]	GHEZELBASH R, MAGHSOUDI A, BIGDELI A, et al. Regional-scale mineralprospectivity mapping: support vector machines and an improved data-driven multi-criteria decision-making technique[J]. Natural Resources Research, 2021, 30(3): 1977-2005.
[47]	MAEPA F, SMITH R S, TESSEMA A. Support vector machine and artificial neural network modelling of orogenic gold prospectivity mapping in the Swayze greenstone belt, Ontario, Canada[J]. Ore Geology Reviews, 2021, 130: 103968.
[48]	ZUO R G, CARRANZA E J M. Support vector machine: a tool for mapping mineral prospectivity[J]. Computers & Geosciences, 2011, 37(12): 1967-1975.
[49]	SUN G T, ZENG Q D, ZHOU J X. Machine learning coupled with mineral geochemistry reveals the origin of oredeposits[J]. Ore Geology Reviews, 2022, 142: 104753.
[50]	CARRANZA E J M, SADEGHI M, BILLAY A. Predictive mapping of prospectivity for orogenic gold, Giyani greenstone belt (South Africa)[J]. Ore Geology Reviews, 2015, 71: 703-718.
[51]	SUN T, CHEN F, ZHONG L X, et al. GIS-based mineral prospectivity mapping using machine learning methods: a case study from Tongling ore district, Eastern China[J]. Ore Geology Reviews, 2019, 109: 26-49.
[52]	ZHENG C J, YUAN F, LUO X R, et al. Mineral prospectivity mapping based on support vector machine and random forest algorithm: a case study from Ashele copper-zinc deposit, Xinjiang, NW China[J]. Ore Geology Reviews, 2023, 159: 105567.
[53]	LI T, ZUO R G, ZHAO X F, et al. Mapping prospectivity for regolith-hosted REE deposits via convolutional neural network with generative adversarial network augmented data[J]. Ore Geology Reviews, 2022, 142: 104693.
[54]	YANG F F, ZUO R G. Geologically constrained convolutional neural network for mineral prospectivity mapping[J]. Mathematical Geosciences, 2024, 56(8): 1605-1628.
[55]	LIU Y, XIA Q L, CARRANZA E J M. Integrating sequential indicator simulation and singularity analysis to analyze uncertainty of geochemical anomaly for exploration targeting of tungsten polymetallic mineralization, Nanling belt, South China[J]. Journal of Geochemical Exploration, 2019, 197: 143-158.
[56]	ZHANG S, XIAO K Y, CARRANZA E J M, et al. Maximum entropy and random forest modeling of mineral potential: analysis of gold prospectivity in the Hezuo-Meiwu district, West Qinling Orogen, China[J]. Natural Resources Research, 2019, 28(3): 645-664.
[57]	CHEN G X, LIU T Y, SUN J S, et al. Gravity method for investigating the geological structures associated with W-Sn polymetallic deposits in the Nanling Range, China[J]. Journal of Applied Geophysics, 2015, 120: 14-25.
[58]	CHEN Y L. Mineral potential mapping with a restricted Boltzmann machine[J]. Ore Geology Reviews, 2015, 71: 749-760.
[59]	CHEN Y L, WU W. Mapping mineral prospectivity using an extreme learning machine regression[J]. Ore Geology Reviews, 2017, 80: 200-213.
[60]	ZUO R G. Geodata science-based mineral prospectivity mapping: a review[J]. Natural Resources Research, 2020, 29(6): 3415-3424.
[61]	ZUO R G, CARRANZA E J M. Machine learning-based mapping for mineral exploration[J]. Mathematical Geosciences, 2023, 55(7): 891-895.
[62]	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
[63]	张振杰, 成秋明, 杨玠, 等. 机器学习与成矿预测: 以闽西南铁多金属矿预测为例[J]. 地学前缘, 2021, 28(3): 221-235. DOI
[64]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32.
[65]	XIANG J, XIAO K Y, CARRANZA E J M, et al. 3D mineral prospectivity mapping with random forests: a case study of Tongling, Anhui, China[J]. Natural Resources Research, 2020, 29(1): 395-414.
[66]	ZHAO J, CHI H Q, SHAO Y Q, et al. Application of AdaBoost algorithms in Fe mineral prospectivity prediction: a case study in Hongyuntan-Chilongfeng mineral district, Xinjiang, China[J]. Natural Resources Research, 2022, 31(4): 2001-2022.
[67]	王学求, 张必敏, 张勤, 等. 国家尺度地球化学填图技术要求[S]. 北京: 中国地质调查局, 2021.
[68]	陈慕天, 王吉勇, 许国明. 老挝川圹省西南部富开铜金矿矿床地质特征[J]. 云南地质, 2013, 32(3): 286-288, 276.
[69]	王宏, 王疆丽, 陈慕天, 等. 老挝川圹省Phu Kham铜金矿床地质特征及找矿方向[J]. 地质找矿论丛, 2014, 29(1): 66-71.
[70]	何文举. 老挝中—东部大型铁铜金矿矿集区矿床地质: 对云南“三江” 地区找金的启示[J]. 云南地质, 2004, 23(2): 164-178.
[71]	赵作新, 王泽传, 朱延浙, 等. 老挝铜矿资源与成矿预测[J]. 地质与资源, 2015, 24(3): 237-241.
[72]	ZHANG Z W, SHU Q, WU C Q, et al. The endogenetic metallogeny of Northern Laos and its relation to the intermediate-felsic magmatism at different stages of the paleotethyan tectonics: a review and synthesis[J]. Ore Geology Reviews, 2020, 123: 103582.
[73]	KAMVONG T, KHIN ZAW, MEFFRE S, et al. Adakites in the Truong Son and loei fold belts, Thailand and Laos: genesis and implications for geodynamics and metallogeny[J]. Gondwana Research, 2014, 26(1): 165-184.
[74]	赵红娟, 陈永清, 卢映祥. 老挝长山成矿带与花岗岩有关的铜金铁矿床的成矿模式[J]. 地质通报, 2011, 30(10): 1619-1627.
[75]	朱华平, 范文玉, 王宏, 等. 老挝色潘铜金矿床研究新进展[J]. 地质科技情报, 2013, 32(5): 182-187.
[76]	陈晓锋, 赵延朋, 张青伟, 等. 老挝班康姆铜金矿成矿流体及成矿物质来源: H-O-He-Ar-C-S-Pb同位素证据[J]. 地质学报, 2021, 95(2): 476-492.
[77]	赵延朋, 莫江平, 王晓曼. 老挝班康姆铜金矿床找矿标志及成矿预测研究[J]. 矿产与地质, 2015, 29(2): 178-182, 188.
[78]	卢见昆, 赵延朋, 陈晓锋, 等. 老挝班康姆铜金矿床成矿作用研究及其指示意义[J]. 矿床地质, 2020, 39(6): 1122-1140.
[79]	王睿. 老挝银水山铜矿矿床地质特征及成因初探[J]. 中国金属通报, 2019(10): 39, 41.
[80]	于江, 张世涛, 唐金晶, 等. 老挝南永铜矿床地质特征及找矿标志[J]. 价值工程, 2014, 33(14): 305-307.
[81]	LU Y X, ZHANG B M, CHI Q H, et al. Continental-scale distribution of tungsten in catchment sediments throughout China: prospecting implications from the China geochemical baselines project[J]. Ore Geology Reviews, 2024, 167: 106021.
[82]	郭林楠, 刘书生, 聂飞, 等. 老挝琅勃拉邦—泰国黎府成矿带古特提斯构造-岩浆演化与金铜成矿作用[J]. 沉积与特提斯地质, 2022, 42(2): 228-241.
[83]	王天瑞, 侯林, 林方成, 等. 老挝—越南长山成矿带古特提斯构造岩浆演化与成矿作用[J]. 沉积与特提斯地质, 2022, 42(2): 212-227.
[84]	王宏. 老挝及邻区构造演化与成矿作用研究[D]. 北京: 中国地质科学院, 2013.
[85]	HUANG J G, REN T, ZOU H J. Genesis of Xinzhai Sandstone[J]. Journal of Earth Science, 20(1): 95-108.
[86]	迟清华, 鄢明才. 应用地球化学元素丰度数据手册[M]. 北京: 地质出版社, 2007.
[87]	AITCHISON J. The statistical analysis of compositional data[M]. London - New York: Chapman and Hall, 1986.
[88]	EGOZCUE J J, PAWLOWSKY-GLAHN V. Groups of parts and their balances in compositional data analysis[J]. Mathematical Geology, 2005, 37(7): 795-828.
[89]	李惠红. 老挝人民民主共和国金属矿产资源分布特征[J]. 西部资源, 2015(5): 74, 84.
[90]	陈喜峰. 东南亚主要优势矿产资源分布规律[J]. 矿物学报, 2015, 35(增刊1): 1073.
[91]	FAWAGREH K, GABER M M, ELYAN E. Random forests: from early developments to recent advancements[J]. Systems Science & Control Engineering, 2014, 2(1): 602-609.
[92]	JAMES G, WITTEN D, HASTIE T, et al. An introduction to statistical learning: with applications in R[M/OL]. New York: Springer US, 2021.
[93]	施俊法, 李友枝, 金庆花, 等. 世界矿情: 亚洲卷[M]. 北京: 地质出版社, 2006.
[94]	郭旻. 老挝万象省纳勐铜多金属矿成矿规律与成矿预测研究[D]. 长沙: 中南大学, 2012.
[95]	张洪瑞, 侯增谦, 杨志明. 特提斯成矿域主要金属矿床类型与成矿过程[J]. 矿床地质, 2010, 29(1): 113-133.

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

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

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

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

综合变量名称	提取的元素组合
B1	U-Th-K₂O-W-Sn 和 Co-Ni
B2	Ag-As-Au-Cu-Mo-Pb-Zn-Sb-Hg-Sn-W 和其他元素