机器学习与成矿预测:以闽西南铁多金属矿预测为例

作为近年来爆炸式发展的方法模型,机器学习为地质找矿提供了新的思维和研究方法.本文探讨矿产预测研究的理论方法体系,总结机器学习在矿产预测领域的特征信息提取和信息综合集成两个方面的应用现状,并讨论机器学习在矿产资源定量预测领域面临的训练样本稀少且不均衡、模型训练中缺乏不确定性评估、缺少反哺研究、方法选择等困难和挑战.进一步...     

Mesozoic magmatism and copper polymetallic mineralization processes in the Shanghang-Datian region, Fujian Province, Southeast China

1IntroductionDuring the Mesozoic there occurred large-scalemagmatism and mineralization in South China.As amain part of East Asian,the South China continent isan extremely complex region,involving multi-stageMesozoic tectono-magmatism.Therefore,various hy…     

Three-dimensional mineral prospectivity modeling for targeting of concealed mineralization within the Zhonggu iron orefield,Ningwu Basin,China

The Zhonggu iron orefield is one of the most important iron orefields in China, and is located in the south of the Ningwu volcanic basin, within the middle and lower Yangtze metallogenic belt of eastern China. Here, we present the results of new 3D prospectivity modeling that enabled the delineation of areas prospective for exploration of concealed and deep-seated Baixiangshan-type mineralization and Yangzhuang-type mineralization within the Zhonggu orefield; both of these deposits are Kiruna-type Fe-apatite deposits but are hosted by different formations within the Ningwu Basin. The modeling approach used during this study involves 3 steps: (1) combining available geological and geophysical data to construct 3D geological models; (2) generation of 3D predictive maps from these 3D geological models using 3D spatial analysis and 3D geophysical methods; (3) combining all of the 3D predictive maps using logistic regression to create a prospectivity map. This approach integrates a large amount of available geoscientific data using 3D methods, including 3D geological modeling, 3D/2D geophysical methods, and 3D spatial analysis and data integration methods. The resulting prospectivity model clearly identifies highly prospective areas that not only include areas of known mineralization but also a number of favorable targets for future mineral exploration. The 3D prospectivity modeling approach showcased within this study provides an efficient way to identify camp-scale concealed and deep-seated exploration targets and can easily be adapted for regional- and deposit- scale targeting.     

Mapping mineral prospectivity using an extreme learning machine regression

In this research, we conduct a case study of mapping polymetallic prospectivity using an extreme learning machine (ELM) regression. A Quad-Core CPU 1.8 GHz laptop computer served as hardware platform. Almeida's Python program was used to construct the ELM regression model to map polymetallic prospectivity of the Lalingzaohuo district in Qinghai Province in China. Based on geologic, metallogenic, and statistical analyses of the study area, one target and eight predictor map patterns and two training sets were then used to train the ELM regression and logistic regression models. ELM regression modeling using the two training sets spends 61.4 s and 65.9 s; whereas the logistic regression modeling using the two training sets spends 1704.0 s and 1628.0 s. The four trained regression models were used to map polymetallic prospectivity. Based on the polymetallic prospectivity predicted by each model, the receiver operating characteristic (ROC) curve was plotted and the area under the curve (AUC) was estimated. The ROC curves show that the two ELM-regression-based models somewhat dominate the two logistic-regression-based models over the ROC performance space; and the AUC values indicate that the overall performances of the two ELM-regression-based models are somewhat better than those of the two logistic-regression-based models. Hence, the ELM-regression-based models slightly outperform the logistic-regression-based models in mapping polymetallic prospectivity. Polymetallic targets were optimally delineated by using the Youden index to maximize spatial association between the delineated polymetallic targets and the discovered polymetallic deposits. The polymetallic targets predicted by the two ELM-regression-based models occupy lower percentage of the study area (2.66–2.68%) compared to those predicted by the two logistic-regression-based models (4.96%) but contain the same percentage of the discovered polymetallic deposits (82%). Therefore, the ELM regression is a useful fast-learning data-driven model that slightly outperforms the widely used logistic regression model in mapping mineral prospectivity. The case study reveals that the magmatic complexes, which intruded into the Baishahe Formation of the Paleoproterozoic Jinshuikou Group or the Carboniferous Dagangou and Shiguaizi Formations, and which were controlled by northwest-western/east-western trending deep faults, are critical for polymetallic mineralization and need to be paid much attention to in future mineral exploration in the study area.     

Comparing BEMD and BEEMD for identifying geochemical anomalies associated with Cu polymetallic mineralization in the southwestern Fujian province (China)

In this paper, Bi-dimensional empirical mode decomposition (BEMD) and bi-dimensional ensemble empirical mode decomposition (BEEMD) are compared to identify geochemical anomalies using a case study from Cu polymetallic mineralization district in southwestern Fujian province (China). The results showed that (1) Both BEMD and BEEMD were useful for decomposing non-linear and non-stationary geochemical data into a set of simple Bi-intrinsic functions (BIMFs), however, there is a drawback of 2D mode mixing in BEMD, and the serious mode mixing can lead to incorrect geological interpretation; (2) BEEMD can give more robust and reliable results than BEMD, making the data easier to interpret; and (3) the BIMFs and the residue obtained by BEEMD can be combined into new components, which can represent geochemical anomalies, unwanted noise and the background of the study area.     

The giant tin polymetallic mineralization in southwest China:Integrated geochemical and isotopic constraints and implications for Cretaceous tectonomagmatic event

The Gejiu-Bozushan-Laojunshan W-Sn polymetallic metallogenic belt(GBLB) in southeast Yunnan Province is an important part of the southwestern Yangtze Block in South China.Tin polymetallic mineralization in this belt includes the Niusipo,Malage,Songshujiao,Laochang and Kafang ore fields in the Gejiu area which are spatially and temporally associated with the Kafang-Laochang and Songshujiao granite plutons.These granites are characterized by variable A/CNK values(mostly 1.1,except for two samples with 1.09),high contents of SiO_2(74.38-76.84 wt.%) and Al_2 O_3(12.46-14.05 wt.%) and variable CaO/Na_2 O ratios(0.2-0.65) as well as high zircon δ~(18)O values(7.74‰-9.86‰),indicative of S-type affinities.These rocks are depleted in Rb,Th,U,Ti,LREE[(La/Yb)N=1.4-20.51],Ba,Nb,Sr,and Ti and display strong negative Eu and Ba anomalies.The rocks possess high Rb/Sr and Rb/Ba ratios,relatively low initial ~(87)Sr/~(86)Sr ratios(0.6917-0.7101),and less radiogenic εNd(t)values(-8.0 to-9.1).The zircon grains from these rocks show negative ε_(Hf)(t) values in the range of-3.7 to-9.9 with mean T_(DM2)(Nd) and T_(DM2)(Hf) values of 1.57 Ga and 1.55 Ga.They show initial ~(207)Pb/~(204)Pb ranging from15.69 to 15.71 and ~(206)Pb/~(204)Pb from 18.36 to 18.70.Monazite from Songshujiao granites exhibits higher U and lower Th/U ratios,lower δ~(18)O values and higher ε_(Hf)(t) values than those of the zircon grains in the KafangLaochang granites.The geochemical and isotopic features indicate that the Laochang-Kafang granites originated by partial melting of Mesoproterozoic crustal components including biotite-rich metapelite and metagraywacke,whereas the Songshujiao granites were derived from Mesoproterozoic muscovite-rich metapelite crustal source.Most zircon grains from the Songshujiao,Laochang and Kafang granites have high-U concentrations and their SIMS U-Pb ages show age scatter from 81.6 Ma to 88.6 Ma,80.7 Ma to 86.1 Ma and 82.3 Ma to 87.0 Ma,suggesting formation earlier than the monazite and cassiterite.Monazite SIMS U-Pb ages and Th-Pb ages of three same granite samples are consistent and show yielded 206 Pb/~(238)U ages of 83.7 ± 0.6 Ma,83.7±0.6 Ma,and 83.4±0.6 Ma,and ~(208)Pb/~(232)Th ages of 83.2 ± 0.5 Ma,83.8 ± 0.4 Ma,and 83.5±0.9 Ma,which are within the range of the SIMS zircon U-Pb ages from these rocks.The data constrain the crystallization of the granites at ca.83 Ma.In situ U-Pb dating of two cassiterite samples from the cassiterite-sulfide ore in the Songshujiao ore field and Kafang ore field,and two from the cassiterite-oxide+cassiterite bearing dolomite in the Laochang ore field yielded weighted mean 206 Pb/~(238)U ages of 83.5±0.4 Ma(MSWD=0.6),83.5 ± 0.4 Ma(MSWD=0.5),83.6 ±0.4 Ma(MSWD=0.6) and 83.2 ±0.7 Ma(MSWD=0.6),respectively.Combined with geological characteristics,the new geochronological data indicate that the formation of the granites and Sn polymetallic deposits are coeval.We correlate the magmatic and metallogenic event with lithospheric thinning and asthenosphere upwelling in continental extension setting in relation to the eastward subduction of the Neo-Tethys beneath the Sanjiang tectonic domain during Late Cretaceous.     

Physicochemical Conditions of Differential Mineralization of Au and As in Gold Deposits,Southwest Guizhou Province,China

The conditions under which gold and arsenic are enriched separately during mineralization in gold deposits in southwestern Guizhou Province were described and the thermodynamic calculations gave: 200–150°C at 400 × 10⁻⁶ -300 × 10⁶ Pa (corresponding to a depth between 1.6 km and 1.2 km); lgf o₂,−40 to -35 Pa; lgf s₂, -20 to−16 Pa; pH 5.0 -4.2 and Eh -0.53 V. This project was jointly supported by the National Natural Science Foundation of China and the Open Lab. of Ore Deposit Geochemistry, Institute of Geochemistry, Chinese Academy of Sciences.     

福建南部大矾山蚀变岩帽的明矾石特征及其找矿指示

含明矾石蚀变岩帽是斑岩-浅成低温热液成矿系统顶部的标志性蚀变,但关于其找矿指向性矿物——明矾石的特征系统地研究不够,特别是如何通过明矾石矿物学特征有效判断蚀变岩帽下伏的成矿潜力,是目前的难题。中国东南沿海地区已探明了以紫金山金-铜矿床、大矾山蚀变岩帽为代表的多个大型斑岩-浅成低温矿床和含明矾石蚀变岩帽,是探讨该问题的理想对象。文章以大矾山蚀变岩帽（面积约8 km²）为研究对象,利用短波红外光谱、电子探针、X射线衍射等技术分析手段,开展明矾石的矿物组合、类型和波谱等方面研究。结果表明,大矾山蚀变岩帽主要蚀变矿物为石英、明矾石、叶腊石、地开石、高岭石、白云母及少量蒙脱石,具有蚀变分带特征,中间主要为石英-明矾石-地开石和地开石-叶腊石蚀变带,南部主要为白云母化-蒙脱石蚀变带,北部为高岭石-白云母蚀变带。研究区的明矾石全为钾质明矾石,按晶形可分为粒状、叶片状和纤维状3种类型,明矾石颗粒普遍发育环带,暗示其形成过程中流体具脉冲式特征。明矾石的短波红外特征吸收峰在1477.69~1479.98 nm之间,具有从东南向西北逐渐变大的趋势,反映出热源可能位于西北部。结合区域地质背景,笔者认为大矾山蚀变岩帽是典型的酸性蚀变岩帽,该区的西北部靠近热源中心,其深部沿断裂带具有寻找浅成低温热液铜（金）矿床的潜力。     

赣中大王山钨多金属矿床流体包裹体及 H-O-S 同位素特征

为确定赣中大王山钨多金属矿床成因类型及地质特征, 笔者对主成矿期石英和硫化矿物进行了流体包裹体、H-O-S 同位素研究。 结合野外矿体产出形态, 可以将研究区划分出3 期成矿作用, 早期以矿囊状为特征, 与围岩无明显的蚀变现象, 主成矿期为大脉状, 与围岩发生云英岩化, 成矿晚期可见含矿石英晶洞。 主成矿期包裹体岩相学和显微测温结果显示： 石英中主要发育气液二相包裹体、富气相包裹体、CO₂三相包裹体和气-液-固三相包裹体 ; 包裹体均一温度为 180 ℃ ～280 ℃（峰值为190 ℃ ～210 ℃）, 盐度为7.86% ～20.22% NaCl_eqv （峰值为11%～17% NaCl_eqv ）, 结合前人对赣中石英脉型黑钨矿中的黑钨矿测温结果, 推测大王山形成于中温、中高盐度;石英包裹体δD_V-SMOW 值介于- 93.1‰～-72.5‰, δ¹⁸O_H2O 值介于0.9‰～3.4‰, 石英包裹体的温度-盐度关系图显示成矿流体混入了低温、低盐度的流体相;δ³⁴S 值介于-1.3‰～+1.9‰之间, 表明成矿物质硫源主要来自深源岩浆。 结合前人研究显示, 黑钨矿较石英早结晶, 成矿流体以岩浆水为主, 大气降水参与成矿, 硫源与深部岩浆有关。 赋矿碱长花岗岩中见有W-Mo 多金属矿囊和细晶岩、伟晶岩脉, 其成岩时间和成矿时间一致。 指示了大王山钨多金属与围岩碱长花岗岩具有一定的亲源性, 并且岩浆-流体液态不混溶作用是导致W-Mo 多金属矿沉淀的主因。     

青海虎头崖矽卡岩型多金属矿床蚀变矿化分带特征研究

虎头崖铜铅锌多金属矿床位于东昆仑西段祁漫塔格成矿亚带内.矿化带产于岩体与围岩接触蚀变带、不同岩性地层接触界面或地层中断裂破碎带内,兼有正接触带和外接触带2种蚀变矿化带.由岩体→接触带→碳酸盐岩地层,金属成矿元素分别为W-Mo→Fe-Sn-Cu→Cu-(Pb-Zn) →Pb-Zn-Ag,蚀变类型由岩体自变质的钾化、硅化、云英岩化过渡为正接触带附近的符山石化、绿帘石化、透辉石化,再到外接触带围岩的石榴子石化、透辉石化,以及晚期的绿泥石化、碳酸盐化.主量元素分析结果显示,地层中的CaO等向岩浆岩内扩散,岩体中的SiO2、Al2O3等则向碳酸盐岩扩散,而且,与花岗岩相比,矽卡岩中FeO、MnO、MgO更为富集,这表明接触渗滤作用与接触交代作用同时存在.成矿元素分析结果显示,W、Mo元素在岩体内含量较高,而Fe、Cu、Pb、Zn主要在矽卡岩带内富集,各成矿元素在未蚀变大理岩中的含量均较低.笔者认为,矿化蚀变的明显分带性是岩体和地层成矿差异性及矽卡岩带内微裂隙系统发育的不均匀性所致.     

福建邵武金坑金多金属矿床成矿时代

邵武金坑金多金属矿床为福建省近年来发现的中型金多金属矿床,位于武夷山成矿带西北部,矿体主要赋存于寒武系林田组层间破碎带中,呈似层状产出,与区内闪长玢岩脉的产状一致.为了查明邵武金坑金多金属矿床的成矿时代,运用LA-ICP-MS方法对侵位于林田组的闪长玢岩进行了锆石U-Pb定年,样品共测试12个数据点,这些206Pb/2...     

Regional prospectivity analysis for hydrothermal-remobilised nickel mineral systems in western Victoria,Australia

Fuzzy logic mineral prospectivity modelling was performed to identify camp-scale areas in western Victoria with an elevated potential for hydrothermal-remobilised nickel mineralisation. This prospectivity analysis was based on a conceptual mineral system model defined for a group of hydrothermal nickel deposits geologically similar to the Avebury deposit in Tasmania. The critical components of the conceptual model were translated into regional spatial predictor maps combined using a fuzzy inference system. Applying additional criteria of land use restrictions and depth of post-mineralisation cover, downgrading the exploration potential of the areas within national parks or with thick barren cover, allowed the identification of just a few potentially viable exploration targets, in the south of the Grampians-Stavely and Glenelg zones. Uncertainties of geological interpretations and parameters of the conceptual mineral system model were explicitly defined and propagated to the final prospectivity model by applying Monte Carlo simulations to the fuzzy inference system. Modelling uncertainty provides additional information which can assist in a further risk analysis for exploration decision making.     

内蒙古西乌旗准好莱西地区铜多金属成矿地质特征及找矿标志

内蒙古西乌旗乌兰哈拉嘎位于兴蒙造山带东南部,区内地层缺失较多,以古生代和中新生代地层为主,岩浆和构造活动较强,地球化学调查显示有明显的异常浓集区。本文从西乌旗乌兰哈拉嘎苏木地区的成矿地质背景着手,分析了区内与成矿有关的地质因素,详细论述了准好莱西铜多金属矿(点)的成矿地质特征,总结了找矿标志。分析认为,该区石炭-二叠系是铜多金属矿的成矿围岩,土壤地球化学异常和航磁异常对找矿的指示意义较大,热液蚀变是最直接的找矿标志。     

粤东金坑锡铜多金属矿燕山期岩浆热液叠加成矿

金坑锡铜多金属矿位于广东莲花山断裂带北东段,是近些年来在粤东地区新发现的典型锡铜多金属矿,关于该矿床的成因类型和成矿机制一直存在较大争议。矿区勘查工作在马山矿段首次发现伴有明显铜矿化的热液隐爆角砾岩,对于揭示矿床成因具有重要意义。LA-ICP-MS锆石U-Pb年代分析结果显示,花岗质角砾成岩年龄约为150 Ma,ε_Hf（t）值为-8.20~-4.55,二阶段Hf模式年龄值为1.73~1.49 Ga,指示岩浆主要来自于中元古代地壳物质,并有地幔物质加入。硫化物原位硫同位素分析结果显示,不同阶段硫化物硫同位素组成具有明显差别。第一阶段（Py-Ⅰ）和第二阶段（Py-Ⅱ）黄铁矿存在显著的硫同位素变化,前者为-0.65‰~1.11‰（n=5）,后者为1.30‰~1.93‰（n=5）,与Py-Ⅱ共生黄铜矿同位素值为1.42‰~1.87‰（n=16）。第三阶段硫化物中黄铜矿δ³⁴S值为3.69‰~4.32‰（n=4）,其中隐爆角砾岩胶结物中黄铜矿（Ccp-Ⅲa）δ³⁴S为3.69‰~3.74‰,略低于第三阶段石英-绿泥石脉中黄铜矿（Ccp-Ⅲb）δ³⁴S值（4.29‰~4.32‰）。第四阶段黄铁矿（Py-Ⅳ）δ³⁴S值为-4.87‰（n=1）,黄铜矿（Ccp-Ⅳ）δ³⁴S值为-3.07‰（n=1）。基于成岩成矿年代及硫化物原位硫同位素分析,文章认为金坑锡铜多金属矿床可能存在两期岩浆热液活动的叠加,其中~150 Ma壳幔混合来源花岗质岩浆活动可能是触发矿区铜矿化的重要岩浆事件,早于后期锡矿的形成（~144 Ma）,这一发现有望为莲花山断裂带锡铜多金属矿指引新的方向。     

Data- and knowledge-driven mineral prospectivity maps for Canada's North

Data- and knowledge-driven techniques are used to produce regional Au prospectivity maps of a portion of Melville Peninsula, Northern Canada using geophysical and geochemical data. These basic datasets typically exist for large portions of Canada's North and are suitable for a “greenfields” exploration programme. The data-driven method involves the use of the Random Forest (RF) supervised classifier, a relatively new technique that has recently been applied to mineral potential modelling while the knowledge-driven technique makes use of weighted-index overlay, commonly used in GIS spatial modelling studies. We use the location of known Au occurrences to train the RF classifier and calculate the signature of Au occurrences as a group from non-occurrences using the basic geoscience dataset. The RF classification outperformed the knowledge-based model with respect to prediction of the known Au occurrences. The geochemical data in general were more predictive of the known Au occurrences than the geophysical data. A data-driven approach such as RF for the production of regional Au prospectivity maps is recommended provided that a sufficient number of training areas (known Au occurrences) exist.     

福建紫金山矿田悦洋银多金属矿床银的赋存状态和沉淀机制

浅成低温热液矿床是世界上银矿的重要矿床类型, 伴生有金铜铅锌等多种金属。银的赋存状态研究可以为矿床资源禀赋、选冶成本以及经济价值的综合评价提供重要的依据。近年来, 矿物自动定量分析系统越来越多地应用到贵金属的赋存状态研究中, 相比传统方法而言其能提供精确定量的矿物学信息。悦洋银多金属矿床位于福建省紫金山矿田, 是典型的浅成低温热液矿床, 是研究银赋存状态的理想选区。通过野外地质调查研究发现, 矿体主要受控于岩性边界和断裂构造, 主要矿石类型为热液角砾岩型和石英脉型。成矿作用可以分为石英-黄铁矿、石英-黄铁矿-黄铜矿、石英-银多金属、石英-碳酸盐等四个阶段, 其中银在石英-银多金属阶段沉淀, 可以进一步划分为石英伊利石硫化物亚阶段和石英冰长石硫化物亚阶段。本文在野外地质调查的基础上, 针对不同的矿石类型使用TIMA(TESCAN Integrated Mineral Analyzer)自动矿物分析系统, 结合显微镜下观察、扫描电镜和电子探针分析手段, 对银的赋存形式和分布情况进行了定量化研究, 根据矿物共生组合对银沉淀机制及成矿过程进行了探讨。研究结果显示, 悦洋矿床中的银90%以上以独立矿物的形式存在, 主要是硫化银和自然银, 且粒径大多在10~50μm之间; 少部分银以次显微包裹体形式存在于黄铜矿中, 或以显微包裹体和类质同相形式存在于黄铁矿和闪锌矿中。成矿热液中银主要以硫氢络合物形式运移, 主成矿期大量的冰长石与银矿物共生表明沸腾作用是主要的沉淀机制。

     

吉林延边红太平铜多金属矿床脉型矿化的成矿时代与构造背景

吉林延边红太平铜多金属矿床位于兴蒙造山带东段,区内发育产于晚古生代火山沉积岩系中的层状铜多金属矿体和受岩体及构造控制的脉状铅锌矿体。为了确定脉型铅锌矿化的成矿时代与构造背景,本文对与脉状铅锌矿体相关的英安岩开展了LA-ICP-MS锆石U-Pb定年及岩石地球化学研究,并对脉状铅锌矿体中金属硫化物开展了Rb-Sr同位素定年。结果表明,英安岩中28个锆石测点的~(206)Pb/~(238)U加权平均年龄为204.1±2.0Ma(MSWD=0.24),脉状铅锌矿石中4件金属硫化物的Rb-Sr等时线年龄为206.8±9.0Ma(MSWD=2.0),二者在误差范围内基本一致,表明红太平矿床脉型铅锌矿化的成矿时代为晚三叠世末期。英安岩的稀土元素配分模式呈明显的轻稀土元素(LREEs)富集,轻重稀土分馏明显[(La/Yb)N=7.59～8.28],存在弱的Eu异常(δEu=0.65～0.68);微量元素以富集大离子亲石元素(LILEs:Rb、Ba和K)和不相容元素(U、Th),亏损高场强元素(HFSEs:Nb、Ta、P和Ti)为特征,表明原始岩浆应为壳-幔混源;脉状铅锌矿体中4件金属硫化物初始Sr同位素比值(87Sr/86Sr)i为0.705954～0.707101(均值0.706390),表明脉型铅锌矿化与壳-幔混源的岩浆作用密切相关。根据Rb-(Yb+Ta)及La/Yb-Th/Yb图解判别结果,结合区域构造演化分析,认为红太平矿区英安岩及相关的脉型铅锌矿化形成于活动大陆边缘的构造环境,与晚三叠世-早侏罗世(T_3-J_1)古太平洋板块向欧亚板块的俯冲作用密切相关。     

江西相山西部地区深部多金属矿化矿石组构学、矿物学研究及其地质意义

江西相山铀矿田西部地区实施的铀矿科学深钻3号孔在深部-700 m发现大量铅锌多金属矿化脉,垂向上呈"上铀下多金属"的分布特征。文章对深部多金属矿化进行了详细的矿物学和矿石组构学研究,并对其成因进行了探讨。研究表明,矿石结构主要有中细粒及微粒结构、自形晶粒状结构、他形晶粒状结构、填隙结构、包含结构、镶边结构、固溶体分离结构、碎裂结构、环带结构等;矿石构造主要有脉状构造、细脉状构造、条带状构造、角砾状构造、致密块状构造、稠密浸染状构造等。矿化类型主要有石英-毒砂-黄铁矿(锡石、黄铜矿)型、黄铁矿型、闪锌矿-方铅矿-黄铁矿型、闪锌矿-方铅矿-碳酸盐(菱铁矿-方解石)型,在空间上具有明显的分带性。根据矿物组合和穿插关系,矿化过程经历了成矿前期的碱性流体作用,形成矿前期绿泥石、锡石和金红石。铅锌成矿期经历了石英-毒砂阶段、黄铁矿化阶段、铅锌矿化阶段、铅锌银碳酸盐阶段等多期叠加。成矿后期以形成碳酸盐-石英脉为特征。综合分析认为,相山深部多金属矿化具有浅成、中低温特征,是与次火山岩有关的低硫化型浅成中低温热液多金属矿化。目前已经发现的铅锌多金属矿化很可能是深部矿化的一个端员,深部很有可能存在与成矿有关的次火山岩体,且具有寻找斑岩型多金属矿化的成矿潜力。     

Back-propagation neural network and support vector machines for gold mineral prospectivity mapping in the Hatu region,Xinjiang, China

Machine Learning technologies have the potential to deliver new nonlinear mineral prospectivity mapping (MPM) models. In this study, Back Propagation (BP) neural network Support Vector Machine (SVM) methods were applied to MPM in the Hatu region of Xinjiang, northwestern China. First, a conceptual model of mineral prospectivity for Au deposits was constructed by analysis of geological background. Evidential layers were selected and transformed into a binary data format. Then, the processes of selecting samples and parameters were described. For the BP model, the parameters of the network were 9–10???1; for the SVM model, a radial basis function was selected as the kernel function with best C?=?1 and γ = 0.25. MPM models using these parameters were constructed, and threshold values of prediction results were determined by the concentration-area (C-A) method. Finally, prediction results from the BP neural network and SVM model were compared with that of a conventional method that is the weight- of- evidence (W- of- E). The prospectivity efficacy was evaluated by traditional statistical analysis, prediction-area (P-A) plots, and the receiver operating characteristic (ROC) technique. Given the higher intersection position (74% of the known deposits were within 26% of the total area) and the larger AUC values (0.825), the result shows that the model built by the BP neural network algorithm has a relatively better prediction capability for MPM. The BP neural network algorithm applied in MPM can elucidate the next investigative steps in the study area.     

Tin mineralization in the Dajing tin–polymetallic deposit, Inner Mongolia, China

Dajing is a large-scale tin–polymetallic deposit that hosts the largest tin mine in North China. It is a hydrothermal vein-type deposit containing Sn, Cu, Pb, Zn, Ag, and minor components Co and In. The deposit consists of more than 690 veins hosted within Upper Permian sedimentary rocks.Three mineralization stages and six ore types are recognized with cassiterite constituting the dominant tin mineral. The SnO₂ content of cassiterite increases in the sequence of mineralization stages shear-deformation→cassiterite–quartz→cassiterite–sulfide (or chalcopyrite–pyrite) stage, while the content of FeO, TiO₂, Nb₂O₅, Ta₂O₅, and In₂O₅ tends to decrease with increases in NiO and Ga₂O₅. It is considered that the negative correlation between SnO₂ and FeO, Nb₂O₅, Ta₂O₅, and In₂O₅ results from elemental substitutions. The early stage cassiterite is much richer in Ta and the later stage cassiterite is much poorer in Ti and Fe than is usual in hydrothermal vein type tin deposits. This is interpreted to indicate that the component of early stage cassiterite reflects a granitic magma source while the composition of later stage cassiterite has a more obvious strata source. The compositional variation of cassiterite corresponds to decreasing crystallization temperatures within each stage and between sequential stages with time. The characteristics of REE in cassiterite from two stages are in accord with that of subvolcanic rocks and the Linxi formation. It suggests that tin transported during the cassiterite–quartz stage may have originated from subvolcanic dikes (e.g., dacite porphyry), while in the cassiterite–sulfide stage, tin may have been derived from wallrock (e.g. siltstone) of the Upper Permian-age Linxi Formation.