机器学习与成矿预测:以闽西南铁多金属矿预测为例

doi:10.13745/j.esf.sf.2021.1.4

摘要/Abstract

摘要：

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。进一步以闽西南马坑式铁矿为实例论述基于机器学习方法的矿产预测基本流程:(1)通过成矿系统研究建立成矿模型,确定矿床控矿要素;(2)通过勘查系统研究建立找矿模型,并为评价预测提供相关的勘查数据;(3)通过预测评价系统研究,建立预测模型,并提取预测要素;(4)利用机器学习模型对预测要素进行信息综合集成,获取成矿有利度图;(5)对预测性能和结果进行不确定性评估;(6)找矿靶区/成矿远景区圈定及资源量估算。最后,总结建立以地学大数据和地球系统理论为指导,以“地球系统-成矿系统-勘查系统-预测评价系统”为研究路线的基于地学大数据的矿产资源定量预测理论和方法体系的研究愿景。

关键词: 矿产预测, 机器学习, 马坑式铁矿

Abstract:

As a rapidly evolving technology in recent years, machine learning (ML) provides a novel approach for mineral prospecting (MP). In this paper, we discuss the progress on the methodology and theory of machine learning and summarize the applications of ML in MP in the areas of pattern recognition/information mining and information integration. We also point out the difficulties and challenges of ML in MP, such as data imbalance, lack of training data, lack of uncertainty evaluation in model selection, feedback feeding, and method selection. Here, we use mineral prospecting of the Makeng-type iron deposit in southwestern Fujian, China as an example to illustrate the process of using the ML method in MP. A complete prediction procedure should include (1) establishing a metallogenic model and identifying ore controlling factors by studying metallogenic systems; (2) building an exploration model and obtaining relevant data by researching exploration systems;(3) establishing a prediction model and extracting predictive factors by researching prediction evaluation systems;(4) obtaining metallogenic probability through information integration of predictive factors using ML models;(5) evaluating uncertainties of prediction performances and results; and (6) delineating prospecting/target areas and estimating resource reserves. Lastly, a future research roadmap for developing big-data based quantitative mineral prospecting theory and methods is proposed, guided by the geological big data and Earth system theory in following the research route of earth system-metallogenic system-exploration system-prediction evaluation system.

Key words: mineral prospectivity, machine learning, Makeng-type iron deposit

中图分类号:

张振杰, 成秋明, 杨玠, 武国朋, 葛云钊. 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.

ZHANG Zhenjie, CHENG Qiuming, YANG Jie, WU Guopeng, GE Yunzhao. Machine learning for mineral prospectivity: A case study of iron-polymetallic mineral prospectivity in southwestern Fujian[J]. Earth Science Frontiers, 2021, 28(3): 221-235.

图/表 10

图1 “成矿系统-勘查系统-预测评价系统”为指导的矿产资源预测研究路线

Fig.1 The research route of metallogenic system-exploration system-prediction evaluation system for mineral prospecting

表1 机器学习及其类别

Table 1 The categories of machine learning

流派	起源	代表性方法模型
符号主义	哲学、心理学、逻辑学	规则学习、决策树
连接主义	神经科学、物理学	神经网络、深度学习
进化主义	遗传学、进化生物学	遗传算法
贝叶斯主义	统计学	朴素贝叶斯、马尔可夫链
类推主义	心理学、运筹学	最近邻算法、支持向量机

图2 马坑铁矿床成矿模式(据文献[20])

Fig.2 Metallogenic model for the Makeng-type iron deposits. Adapted from[20].

图3 闽西南马坑式铁矿成矿模型-找矿模型转化

Fig.3 Transformation of metallogenic model to exploration model for the Makeng-type iron deposits in southwestern Fujian

图4 闽西南马坑式铁矿找矿模型-预测模型转化及预测图层提取方法

Fig.4 Transformation of exploration model to prospecting model, and the method for prediction layer extraction for the Makeng-type iron deposits in southwestern Fujian

图5 闽西南马坑式铁矿“五要素”预测图层

Fig.5 Five predictive factors for the Makeng-type iron deposits in southwestern Fujian

图6 闽西南马坑式铁矿预测结果

Fig.6 Prediction results from four prediction models for the Makeng-type iron deposits in southwestern Fujian

表2 混淆矩阵组成

Table 2 Elements of the confusion matrix

混淆矩阵		预测值
混淆矩阵		矿	非矿
实际值	矿	TP(10)	FN(5)
实际值	非矿	FP(2)	TN(13)

图7 闽西南马坑式铁矿预测结果ROC评估(据文献[20])

Fig.7 ROC evaluations of the prediction results from four prediction models. Adapted from [20].

图8 闽西南马坑式铁矿成矿远景区圈定依据

Fig.8 Basis for delineating the metallogenic prospective area in the Makeng-type deposits in southwestern Fujian

参考文献 113

[1]	SINGER D, MENZIE W D. Quantitative mineral resource assessments[M]. Oxford: Oxford University Press, 2010: 4-5.
[2]	AGTERBERG F P, KELLY A M. Geomathematical methods for use in prospecting[J]. Canadian Mining Journal, 1971, 92(5):61-72.
[3]	SINGER D A, MOSIER D L. A review of regional mineral resource assessment methods[J]. Economic Geology, 1981, 76(5):1006-1015. DOI URL
[4]	HARRIS D P. Mineral resources appraisal: mineral endowment, resources, and potential supply: concepts, methods and cases[M]. Oxford: Oxford University Press, 1984: 1-460.
[5]	BONHAM-CARTER G F, AGTERBERG F P, WRIGHT D F. Weights of evidence modelling: a new approach to mapping mineral potential[M]. Ottawa: Geological Survey of Canada, 1989: 171-183.
[6]	成秋明. 非线性成矿预测理论: 多重分形奇异性-广义自相似性-分形谱系模型与方法[J]. 地球科学: 中国地质大学学报, 2006, 31(3):337-348.
[7]	赵鹏大. 大数据时代数字找矿与定量评价[J]. 地质通报, 2015, 34(7):1255-1259.
[8]	肖克炎, 孙莉, 李楠, 等. 大数据思维下的矿产资源评价[J]. 地质通报, 2015, 34(7):1266-1272.
[9]	周永章, 黎培兴, 王树功, 等. 矿床大数据及智能矿床模型研究背景与进展[J]. 矿物岩石地球化学通报, 2017, 36(2):327-331, 344.
[10]	王语, 周永章, 肖凡, 等. 基于成矿条件数值模拟和支持向量机算法的深部成矿预测: 以粤北凡口铅锌矿为例[J]. 大地构造与成矿学, 2020, 44(2):222-230.
[11]	ZUO R G, CARRANZA E J M. Support vector machine: a tool for mapping mineral prospectivity[J]. Computers & Geosciences, 2011, 37(12):1967-1975. DOI URL
[12]	MAO X C, ZHANG W, LIU Z K, et al. 3D mineral prospectivity modeling for the low-sulfidation epithermal gold deposit: a case study of the Axi gold deposit, western Tianshan, NW China[J]. Minerals, 2020, 10(3):233. DOI URL
[13]	李苍柏, 肖克炎, 李楠, 等. 支持向量机、随机森林和人工神经网络机器学习算法在地球化学异常信息提取中的对比研究[J]. 地球学报, 2020, 41(2):309-319.
[14]	刘艳鹏, 朱立新, 周永章. 大数据挖掘与智能预测找矿靶区实验研究: 卷积神经网络模型的应用[J]. 大地构造与成矿学, 2020, 44(2):192-202.
[15]	LI H, LI X H, YUAN F, et al. Convolutional neural network and transfer learning based mineral prospectivity modeling for geochemical exploration of Au mineralization within the Guandian-Zhangbaling area, Anhui Province, China[J]. Applied Geochemistry, 2020, 122:104747. DOI URL
[16]	陈进, 毛先成, 刘占坤, 等. 基于随机森林算法的大尹格庄金矿床三维成矿预测[J]. 大地构造与成矿学, 2020, 44(2):231-241.
[17]	张士红, 肖克炎. 基于随机森林的四川省会理地区 “拉拉式” 铜矿成矿预测[J]. 地质与勘探, 2020, 56(2):239-252.
[18]	邓浩, 郑扬, 陈进, 等. 基于深度学习的山东大尹格庄金矿床深部三维预测模型[J]. 地球学报, 2020, 41(2):157-165.
[19]	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. DOI URL
[20]	ZHANG Z J, ZUO R G, XIONG Y H. A comparative study of fuzzy weights of evidence and Random Forests for mapping mineral prospectivity for skarn-type Fe deposits in the Southwestern Fujian metallogenic belt, China[J]. Science China Earth Sciences, 2016, 59(3):556-572. DOI URL
[21]	CHEN Y L, LU L J, LI X B. Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly[J]. Journal of Geochemical Exploration, 2014, 140:56-63. DOI URL
[22]	XIONG Y H, ZUO R G. Recognition of geochemical anomalies using a deep autoencoder network[J]. Computers & Geosciences, 2016, 86:75-82. DOI URL
[23]	ZUO R G, XIONG Y H. Big data analytics of identifying geochemical anomalies supported by machine learning methods[J]. Natural Resources Research, 2018, 27(1):5-13. DOI URL
[24]	CHEN Y L, WU W, ZHAO Q Y. A bat algorithm-based data-driven model for mineral prospectivity mapping[J]. Natural Resources Research, 2020, 29(1):247-265. DOI URL
[25]	陈毓川, 裴荣富, 王登红. 三论矿床的成矿系列问题[J]. 地质学报, 2006, 80(10):1501-1508.
[26]	程裕淇, 陈毓川, 赵一鸣. 初论矿床的成矿系列问题[J]. 中国地质科学院院报, 1979, 1(1):32-58.
[27]	程裕淇, 陈毓川, 赵一鸣, 等. 再论矿床的成矿系列问题[J]. 中国地质科学院院报, 1983, 5(6):1-66.
[28]	赵鹏大, 孟宪国. 地质异常与矿床预测[J]. 地球科学: 中国地质大学学报, 1993, 18(1):39-47.
[29]	翟裕生. 论成矿系统[J]. 地学前缘, 1999, 6(1):13-27.
[30]	翟裕生. 试论矿床成因的基本模型[J]. 地学前缘, 2014, 21(1):1-8.
[31]	SINGER D A. Basic concepts in three-part quantitative assessments of undiscovered mineral resources[J]. Nonrenewable Resources, 1993, 2(2):69-81. DOI URL
[32]	赵鹏大. “三联式” 资源定量预测与评价: 数字找矿理论与实践探讨[J]. 地球科学: 中国地质大学学报, 2002, 27(5):482-489.
[33]	赵鹏大, 陈建平, 张寿庭. “三联式” 成矿预测新进展[J]. 地学前缘, 2003, 10(2):455-463.
[34]	王世称, 杨毅恒, 严光生, 等. 全国超大型、大型金矿定量预测方法研究[J]. 地质论评, 2000, 46(S1):17-24.
[35]	王世称. 综合信息矿产预测理论与方法体系新进展[J]. 地质通报, 2010, 29(10):1399-1403.
[36]	CHENG Q M, AGTERBERG F P, BALLANTYNE S B. The separation of geochemical anomalies from background by fractal methods[J]. Journal of Geochemical Exploration, 1994, 51(2):109-130. DOI URL
[37]	CHENG Q M, AGTERBERG F P. Fuzzy weights of evidence method and its application in mineral potential mapping[J]. Natural Resources Research, 1999, 8(1):27-35. DOI URL
[38]	CHENG Q M, XU Y G, GRUNSKY E. Integrated spatial and spectrum method for geochemical anomaly separation[J]. Natural Resources Research, 2000, 9(1):43-52. DOI URL
[39]	CHENG Q M. Mapping singularities with stream sediment geochemical data for prediction of undiscovered mineral deposits in Gejiu, Yunnan Province, China[J]. Ore Geology Reviews, 2007, 32(1/2):314-324. DOI URL
[40]	成秋明. 覆盖区矿产综合预测思路与方法[J]. 地球科学: 中国地质大学学报, 2012, 37(6):1109-1125.
[41]	NAEINI E Z, PRINDLE K. Machine learning and learning from machines[J]. The Leading Edge, 2018, 37(12):886-893. DOI URL
[42]	DOMINGOS P. The master algorithm: how the quest for the ultimate learning machine will remake our world[M]. New York: Basic Books, 2015: 23-56.
[43]	MITCHELL T M. Machine learning and data mining[J]. Communications of the ACM, 1999, 42(11):30-36.
[44]	CRACKNELL M J, READING A M. Geological mapping using remote sensing data: a comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information[J]. Computers & Geosciences, 2014, 63:22-33. DOI URL
[45]	CRACKNELL M J, READING A M, MCNEILL A W. Mapping geology and volcanic-hosted massive sulfide alteration in the Hellyer-Mt Charter region, Tasmania, using Random Forests^TM and Self-Organizing Maps[J]. Australian Journal of Earth Sciences, 2014, 61(2):287-304. DOI URL
[46]	GRUNSKY E C, MUELLER U A, CORRIGAN D. A study of the lake sediment geochemistry of the Melville Peninsula using multivariate methods: applications for predictive geological mapping[J]. Journal of Geochemical Exploration, 2014, 141:15-41. DOI URL
[47]	HARRIS J R, GRUNSKY E C. Predictive lithological mapping of Canada’s North using Random Forest classification applied to geophysical and geochemical data[J]. Computers & Geosciences, 2015, 80:9-25. DOI URL
[48]	GRUNSKY E C, DE CARITAT P. State-of-the-art analysis of geochemical data for mineral exploration[J]. Geochemistry: Exploration, Environment, Analysis, 2020, 20(2):217-232. DOI URL
[49]	左仁广. 基于深度学习的深层次矿化信息挖掘与集成[J]. 矿物岩石地球化学通报, 2019, 38(1):53-60, 203.
[50]	CARRANZA E J M. Geocomputation of mineral exploration targets[J]. Computers & Geosciences, 2011, 37(12):1907-1916. DOI URL
[51]	PORWAL A, CARRANZA E J M, HALE M. A hybrid fuzzy weights-of-evidence model for mineral potential mapping[J]. Natural Resources Research, 2006, 15(1):1-14. DOI URL
[52]	AGTERBERG F P, BONHAM-CARTER G F, CHENG Q M, et al. Weights of evidence modeling and weighted logistic regression for mineral potential mapping[M]//Computers in geology: 25 years of progress. Oxford: Oxford University Press, 1993: 13-32.
[53]	SINGER D A, KOUDA R. Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, Japan[J]. Mathematical Geology, 1996, 28(8):1017-1023. DOI URL
[54]	PORWAL A, CARRANZA E J M, HALE M. Artificial neural networks for mineral-potential mapping: a case study from Aravalli Province, western India[J]. Natural Resources Research, 2003, 12(3):155-171. DOI URL
[55]	BROWN W M, GEDEON T D, GROVES D I, et al. Artificial neural networks: a new method for mineral prospectivity mapping[J]. Australian Journal of Earth Sciences, 2000, 47(4):757-770. DOI URL
[56]	LEWKOWSKI C, PORWAL A, GONZÁLEZ-ÁLVAREZ I. Genetic programming applied to base-metal prospectivity mapping in the Aravalli Province, India[C]. Vienna: EGU General Assembly Conference Abstracts, 2010: 523.
[57]	张振飞, 高凤亮, 马智民, 等. 基于GIS的单元簇遗传建模及其在区域矿产预测中的应用[J]. 西安工程学院学报, 2001, 23(3):15-19.
[58]	ABEDI M, NOROUZI G H, BAHROUDI A. Support vector machine for multi-classification of mineral prospectivity areas[J]. Computers & Geosciences, 2012, 46:272-283. DOI URL
[59]	XIONG Y H, ZUO R G. Recognizing multivariate geochemical anomalies for mineral exploration by combining deep learning and one-class support vector machine[J]. Computers & Geosciences, 2020, 140:104484. DOI URL
[60]	PORWAL A, YU L. SVM-based base-metal prospectivity modeling of the Aravalli Orogen, northwestern India[C]. Vienna: EGU General Assembly Conference Abstracts, 2010: 7542.
[61]	CARRANZA E J M, LABORTE A G. Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (the Philippines)[J]. Computers & Geosciences, 2015, 74:60-70. DOI URL
[62]	GAO Y, ZHANG Z J, XIONG Y H, et al. Mapping mineral prospectivity for Cu polymetallic mineralization in southwest Fujian Province, China[J]. Ore Geology Reviews, 2016, 75:16-28. DOI URL
[63]	RODRIGUEZ-GALIANO V F, CHICA-OLMO M, CHICA-RIVAS M. Predictive modelling of gold potential with the integration of multisource information based on Random Forest: a case study on the Rodalquilar area, Southern Spain[J]. International Journal of Geographical Information Science, 2014, 28(7):1336-1354. DOI URL
[64]	CARRANZA E J M, LABORTE A G. Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: application of Random Forests algorithm[J]. Ore Geology Reviews, 2015, 71:777-787. DOI URL
[65]	向杰, 陈建平, 肖克炎, 等. 基于机器学习的三维矿产定量预测: 以四川拉拉铜矿为例[J]. 地质通报, 2019, 38(12):2010-2021.
[66]	LI T, ZUO R G, XIONG Y H, et al. Random-drop data augmentation of deep convolutional neural network for mineral prospectivity mapping[J]. Natural Resources Research, 2021, 30(1):27-38. DOI URL
[67]	蔡惠慧, 徐永洋, 李孜轩, 等. 基于卷积神经网络模型划分成矿远景区: 以甘肃大桥地区金多金属矿田为例[J]. 地质通报, 2019, 38(12):1999-2009.
[68]	李诗, 陈建平, 向杰, 等. 基于AlexNet网络的二维找矿预测: 以松桃—花垣地区沉积型锰矿为例[J]. 地质通报, 2019, 38(12):2022-2032.
[69]	LI S, CHEN J P, XIANG J. Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional geological big data[J]. Neural Computing and Applications, 2020, 32(7):2037-2053. DOI URL
[70]	SUN T, LI H, WU K X, et al. Data-driven predictive modelling of mineral prospectivity using machine learning and deep learning methods: a case study from southern Jiangxi Province, China[J]. Minerals, 2020, 10(2):102. DOI URL
[71]	左仁广, 彭勇, 李童, 等. 基于深度学习的地质找矿大数据挖掘与集成的挑战[J]. 地球科学, 2021, 46(1):350-358.
[72]	CARRANZA E J M, HALE M, FAASSEN C. Selection of coherent deposit-type locations and their application in data-driven mineral prospectivity mapping[J]. Ore Geology Reviews, 2008, 33(3/4):536-558. DOI URL
[73]	高原. 闽西南铜多金属矿找矿信息挖掘与成矿预测[D]. 武汉: 中国地质大学, 2019: 89-94.
[74]	GRANEK J. Application of machine learning algorithms to mineral prospectivity mapping[D]. Vancouver: University of British Columbia, 2016: 8-14, 56-69.
[75]	ZUO R G, WANG Z Y. Effects of random negative training samples on mineral prospectivity mapping[J]. Natural Resources Research, 2020, 29(6):3443-3455. DOI URL
[76]	季斌, 周涛发, 张达玉, 等. 大数据环境下内蒙古浩布高地区铅锌多金属矿智能矿产预测研究[J]. 地质科学, 2018, 53(4):1347-1360.
[77]	ABEDI M, NOROUZI G H, TORABI S A. Clustering of mineral prospectivity area as an unsupervised classification approach to explore copper deposit[J]. Arabian Journal of Geosciences, 2013, 6(10):3601-3613. DOI URL
[78]	LU J, GONG P H, YE J P, et al. Learning from very few samples: a survey[J]. arXiv: 2009. 02653v2.
[79]	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: 10.13745/j.esf.sf.2020.12.1. DOI
[80]	WANG Z Y, YIN Z, CAERS J, et al. A Monte Carlo-based framework for risk-return analysis in mineral prospectivity mapping[J]. Geoscience Frontiers, 2020, 11(6):2297-2308. DOI URL
[81]	HJORT N L, CLAESKENS G. Frequentist model average estimators[J]. Journal of the American Statistical Association, 2003, 98(464):879-899. DOI URL
[82]	CHENG Q M, OBERHÄNSLI R, ZHAO M L. Anew international initiative for facilitating data-driven Earth science transformation[J]. Geological Society of London, Special Publications, 2020: SP499-2019-158.
[83]	WOLPERT D H, MACREADY W G. No free lunch theorems for search[R]. Santa Fe: Santa Fe Institute, Technical Report SFI-TR-95-02-010, 1995.
[84]	WRIGHT D F. Evaluating volcanic-hosted massive sulphide favourability using GIS-based spatial data integration models, Snow Lake area, Manitoba[D]. Ottawa: University of Ottawa, 1996: 217-235.
[85]	HRONSKY J M A, KREUZER O P. Applying spatial prospectivity mapping to exploration targeting: fundamental practical issues and suggested solutions for the future[J]. Ore Geology Reviews, 2019, 107:647-653. DOI URL
[86]	FORD A, PETERS K J, PARTINGTON G A, et al. Translating expressions of intrusion-related mineral systems into mappable spatial proxies for mineral potential mapping: case studies from the Southern New England Orogen, Australia[J]. Ore Geology Reviews, 2019, 111. DOI: 10.1016/j.oregeorev.2019.102943. DOI
[87]	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. DOI URL
[88]	ZUO R G. Geodata science-based mineral prospectivity mapping: a review[J]. Natural Resources Research, 2020, 29(6):3415-3424. DOI URL
[89]	左仁广, 夏庆霖, 张道军, 等. 基于地质过程的闽西南马坑式铁多金属矿定量预测[J]. 地球科学: 中国地质大学学报, 2012, 37(6):1183-1190.
[90]	ZUO R G, ZHANG Z J, ZHANG D J, et al. Evaluation of uncertainty in mineral prospectivity mapping due to missing evidence: a case study with skarn-type Fe deposits in Southwestern Fujian Province, China[J]. Ore Geology Reviews, 2015, 71:502-515. DOI URL
[91]	WANG Z Y, DONG Y N, ZUO R G. Mapping geochemical anomalies related to Fe-polymetallic mineralization using the maximum margin metric learning method[J]. Ore Geology Reviews, 2019, 107:258-265. DOI URL
[92]	XIONG Y H, ZUO R G. GIS-based rare events logistic regression for mineral prospectivity mapping[J]. Computers & Geosciences, 2018, 111:18-25. DOI URL
[93]	XIONG Y H, ZUO R G, CARRANZA E J M. Mapping mineral prospectivity through Big Data analytics and a deep learning algorithm[J]. Ore Geology Reviews, 2018, 102:811-817. DOI URL
[94]	葛朝华, 韩发, 邹天人, 等. 马坑铁矿火山沉积成因探讨[J]. 中国地质科学院院报, 1981, 3(1):47-69.
[95]	赵一鸣, 谭惠静, 许振南, 等. 闽西南地区马坑式钙夕卡岩型铁矿床专辑1[J]. 中国地质科学院矿床地质研究所所刊, 1983(1):1-141.
[96]	洪大卫, 陈学正, 李纯杰, 等. 闽西南某些燕山期花岗岩的岩石学特征及其与铁矿成矿关系的探讨(1978)[J]. 中国地质科学院矿床地质研究所所刊, 1986(2):71-72.
[97]	ZHANG Z J, ZUO R G, CHENG Q M. The mineralization age of the Makeng Fe deposit, South China: implications from U-Pb and Sm-Nd geochronology[J]. International Journal of Earth Sciences, 2015, 104(3):663-682. DOI URL
[98]	ZHANG Z J, ZUO R G, CHENG Q M. Geological features and formation processes of the Makeng Fe deposit, China[J]. Resource Geology, 2015, 65(3):266-284. DOI URL
[99]	ZHANG Z J, ZUO R G. Iron isotope systematics of magnetite: implications for the Genesis of Makeng iron deposit, Southern China[J]. Acta Geologica Sinica, 2013, 87(Suppl):840-843.
[100]	ZHANG Z J, ZUO R G. Sr-Nd-Pb isotope systematics of magnetite: implications for the Genesis of Makeng Fe deposit, Southern China[J]. Ore Geology Reviews, 2014, 57:53-60. DOI URL
[101]	ZHAO X L, ZHANG Y J, JIANG Y, et al. Determining the origin of the Makeng Fe deposit, Fujian Province, China[J]. Journal of Geochemical Exploration, 2020, 213:106523. DOI URL
[102]	YANG Y L, NI P, PAN J Y, et al. Constraints on the mineralization processes of the Makeng iron deposit, Eastern China: fluid inclusion, H-O isotope and magnetite trace element analysis[J]. Ore Geology Reviews, 2017, 88:791-808. DOI URL
[103]	AKAIKE H. A new look at the statistical model identification[J]. IEEE Transactions on Automatic Control, 1974, 19(6):716-723. DOI URL
[104]	SCHWARZ G. Estimating the dimension of a model[J]. The Annals of Statistics, 1978, 6(2):461-464.
[105]	METZ C E. Basic principles of ROC analysis[J]. Seminars in Nuclear Medicine, 1978, 8(4):283-298. DOI URL
[106]	HANLEY J A, MCNEIL B J. The meaning and use of the area under a receiver operating characteristic (ROC) curve[J]. Radiology, 1982, 143(1):29-36. DOI URL
[107]	JENKS G F. Optimal data classification for choropleth maps[D]. Lawrence: University of Kansas, 1977.
[108]	滕吉文. 地球深部物质和能量交换的动力过程与矿产资源的形成[J]. 大地构造与成矿学, 2003, 27(1):3-21.
[109]	滕吉文, 杨立强, 姚敬全, 等. 金属矿产资源的深部找矿、勘探与成矿的深层动力过程[J]. 地球物理学进展, 2007, 22(2):317-334.
[110]	翟裕生. 地球系统、成矿系统到勘查系统[J]. 地学前缘, 2007, 14(1):172-181.
[111]	成秋明. 成矿过程奇异性与矿床多重分形分布[J]. 矿物岩石地球化学通报, 2008, 27(3):298-305.
[112]	汪品先. 对地球系统科学的理解与误解: 献给第三届地球系统科学大会[J]. 地球科学进展, 2014, 29(11):1277-1279.
[113]	赵鹏大. 成矿定量预测与深部找矿[J]. 地学前缘, 2007, 14(5):1-10.