Key issues in three-dimensional predictive modeling of mineral prospectivity

doi:10.13745/j.esf.sf.2024.5.9

Abstract

Abstract:

Three-dimensional predictive modeling of mineral prospectivity is an important approach to deep mineral exploration. Although significant advancements have been made in the methodology and application of this approach, several key scientific and technological issues remain unresolved concerning the insufficiencies of multi-scale 3D predictive modeling methodology, uncertainty analysis and optimization of prediction results, mining of key factors in 3D mineralization prediction, and dedicated 3D deep learning models and methodologies tailored for 3D predictive modeling of mineral prospectivity. Focusing on these key issues, this paper conducts a comprehensive review of current research progress in the field, and proposes potential solutions and research directions to address these issues. Future developments in this field include methods for deep mining of 3D predictive information; applicable 3D deep learning models and training methods for enhanced predictive modeling; uncertainty analysis and optimization methods for improving the reliability and accuracy of 3D mineralization prediction; and a methodological framework for multi-scale predictive modeling so as to effectively guide deep mineral exploration at the levels of orebodies, ore fields, and ore deposits. Resolving these key issues will further develop and refine the theoretical and methodological frameworks of 3D mineralization prediction, significantly improve the efficiency of deep mineral exploration, and ultimately facilitate breakthrough in mineral deposit discovery in the deep earth.

Key words: 3D mineral prospectivity prediction, key issues, multi-scale, predictive information discovery, uncertainty, data fusion

CLC Number:

P624
P628

YUAN Feng, LI Xiaohui, TIAN Weidong, ZHOU Guanqun, WANG Jinju, GE Can, GUO Xianzheng, ZHENG Chaojie. Key issues in three-dimensional predictive modeling of mineral prospectivity[J]. Earth Science Frontiers, 2024, 31(4): 119-128.

Figures/Tables 5

Fig.1 Key issues in 3D mineralization prediction

Fig.2 Mining of key factors in 3D mineral prospectivity prediction. (a) Three-Dimensional physical property inversion (adapted from [26]). (b) Trace elements in altered minerals as an indicator for porphyry system center (adapted from [29]). (c) Numerical simulation of 3D mineralization process and volumetric strain increment (adapted from [16]). (d) Chemical reaction rate and intensity of mineralization (adapted from [32-33]).

Fig.3 Deep learning for mineral prospectivity prediction. (a) Architecture of the proposed multi-scale 3D convolutional neural network. (b) Construction of the 3D sample set. (c) Method for training with a small sample size.

Fig.4 Uncertainty analysis on 3D geological model (a, adapted from [76]), prediction data loss (b, adapted from [78]), and 3D prediction result (c, adapted from [77]).

Fig.5 Multi-scale 3D geological model. Modified after [19,75,88⇓-90].

References 92

[10]	肖克炎, 李楠, 孙莉, 等. 基于三维信息技术大比例尺三维立体矿产预测方法及途径[J]. 地质学刊, 2012, 36(3): 229-236.
[11]	袁峰, 李晓晖, 张明明, 等. 隐伏矿体三维综合信息成矿预测方法[J]. 地质学报, 2014, 88(4): 630-643.
[12]	毛先成, 张苗苗, 邓浩, 等. 矿区深部隐伏矿体三维可视化预测方法[J]. 地质学刊, 2016, 40(3): 363-371.
[13]	袁峰, 张明明, 李晓晖, 等. 成矿预测: 从二维到三维[J]. 岩石学报, 2019, 35(12): 3863-3874.
[14]	NIELSEN S H H, CUNNINGHAM F, HAY R, et al. 3D prospectivity modelling of orogenic gold in the Marymia Inlier, Western Australia[J]. Ore Geology Reviews, 2015, 71: 578-591.
[15]	PAYNE C E, CUNNINGHAM F, PETERS K J, et al. From 2D to 3D: prospectivity modelling in the taupo volcanic zone, new zealand[J]. Ore Geology Reviews, 2015, 71: 558-577.
[16]	LI X H, YUAN F, ZHANG M M, et al. 3D computational simulation-based mineral prospectivity modeling for exploration for concealed Fe-Cu skarn-type mineralization within the Yueshan orefield, Anqing district, Anhui Province, China[J]. Ore Geology Reviews, 2019, 105: 1-17.
[17]	FU G M, LÜ Q T, YAN J Y, et al. 3D mineral prospectivity modeling based on machine learning: a case study of the Zhuxi tungsten deposit in northeastern Jiangxi Province, South China[J]. Ore Geology Reviews, 2021, 131: 104010.
[18]	DENG H, ZHENG Y, CHEN J, et al. Learning 3D mineral prospectivity from 3D geological models using convolutional neural networks: application to a structure-controlled hydrothermal gold deposit[J]. Computersand Geosciences, 2022, 161: 105074.
[19]	LI X H, XUE C, CHEN Y H, et al. 3D convolutional neural Network-based 3D mineral prospectivity modeling for targeting concealed mineralization within Chating Area, middle-Lower Yangtze River metallogenic Belt, China[J]. Ore Geology Reviews, 2023, 157: 105444.
[20]	毛先成, 邹艳红, 陈进, 等. 隐伏矿体三维可视化预测[M]. 长沙: 中南大学出版社, 2011: 1-170.
[21]	陈建平, 董庆吉, 郝金华, 等. 基于GIS的证据权重法青海“三江” 北段斑岩型钼铜矿产资源成矿预测[J]. 岩石矿物学杂志, 2011, 30(3): 519-529.
[22]	YUAN F, LI X H, ZHANG M M, et al. Three-dimensional weights of evidence-based prospectivity modeling: a case study of the Baixiangshan mining area, Ningwu Basin, Middle and Lower Yangtze Metallogenic Belt, China[J]. Journal of Geochemical Exploration, 2014, 145: 82-97.
[23]	DENG H, HUANG X F, MAO X C, et al. Generalized mathematical morphological method for 3D shape analysis of geological boundaries: application in identifying mineralization-associated shape features[J]. Natural Resources Research, 2022, 31(4): 2103-2127.
[24]	LÜ Q T, QI G, YAN J Y. 3D geologic model of Shizishan ore field constrained by gravity and magnetic interactive modeling: a case history[J]. Geophysics, 2013, 78(1): B25-B35.
[25]	严加永, 吕庆田, 陈向斌, 等. 基于重磁反演的三维岩性填图试验: 以安徽庐枞矿集区为例[J]. 岩石学报, 2014, 30(4): 1041-1053.
[26]	LI X H, YUAN F, ZHANG M M, et al. Three-dimensional mineral prospectivity modeling for targeting of concealed mineralization within the Zhonggu iron orefield, Ningwu Basin, China[J]. Ore Geology Reviews, 2015, 71: 633-654.
[27]	ZHANG Z Q, WANG G W, CARRANZA E J M, et al. Metallogenic model of the Wulong gold district, China, and associated assessment of exploration criteria based on multi-scale geoscience datasets[J]. Ore Geology Reviews, 2019, 114: 103138.
[28]	LI X H, YUAN F, JOWITT S M, et al. Singularity mapping of fracture fills and its relationship to deep concealed orebodies: a case study of the Shaxi porphyry Cu-Au deposit, China[J]. Geochemistry: Exploration, Environment, Analysis, 2017, 17(3): 252-260.
[29]	COOKE D R, WILKINSON J J, BAKER M, et al. Usingmineral chemistry to aid exploration: a case study from the resolution porphyry Cu-Mo deposit, Arizona[J]. Economic Geology, 2020, 115(4): 813-840.
[30]	陈华勇, 肖兵, 张世涛, 等. 蚀变矿物勘查标识体系[M]. 北京: 科学出版社, 2021.
[31]	李程. 深部地质地球化学三维定量矿产预测方法研究: 以西秦岭早子沟金矿为例[D]. 成都: 成都理工大学, 2021.
[32]	HU X Y, LI X H, YUAN F, et al. Numerical modeling of ore-forming processes within the Chating Cu-Au porphyry-type deposit, China: implications for the longevity of hydrothermal systems and potential uses in mineral exploration[J]. Ore Geology Reviews, 2020, 116: 103230.
[33]	戴文强. 安庆铜矿床热液蚀变及成矿过程数值模拟研究[D]. 合肥: 合肥工业大学, 2020.
[34]	WEIS P, DRIESNER T, HEINRICH C A. Porphyry-copper ore shells form at stable pressure-temperature fronts within dynamic fluid plumes[J]. Science, 2012, 338(6114): 1613-1616. DOI PMID
[35]	QIN Y Z, LIU L M. Quantitative 3D association of geological factors and geophysical fields with mineralization and its significance for ore prediction: an example from Anqing orefield, China[J]. Minerals, 2018, 8(7): 300.
[36]	袁峰, 李晓晖, 胡训宇, 等. 热液矿床成矿作用研究新途径: 数值模拟[J]. 地质科学, 2019, 54(3): 678-690.
[37]	安文通, 陈建平, 朱鹏飞. 基于成矿过程数值模拟的隐伏矿双向预测研究[J]. 地学前缘, 2021, 28(3): 97-111. DOI
[38]	谢绍锋. 胶西北矿集区成矿数值模拟与隐伏矿体三维预测研究[D]. 长沙: 中南大学, 2022.
[39]	毕晨曦, 刘亮明, 周飞虎. 融合动力学模拟的机器学习三维成矿预测: 以安徽铜山铜矿为例[J/OL]. 大地构造与成矿学, 2023: 1-16. DOI:10.16539/j.ddgzyckx.2023.01.104.
[40]	LIU L M, WAN C L, ZHAO C B, et al. Geodynamic constraints on orebody localization in the Anqing orefield, China: computational modeling and facilitating predictive exploration of deep deposits[J]. Ore Geology Reviews, 2011, 43(1): 249-263.
[41]	贾蔡, 袁峰, 李晓晖, 等. 基于多源数据约束的成矿动力学模拟: 以宁芜盆地钟姑矿田典型矿床为例[J]. 地质科学, 2018, 53(4): 1327-1346.
[42]	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.
[43]	黄沁怡, 李增华, 许德如, 等. 多过程耦合动力学数值模拟在热液矿床研究中的应用及发展前景[J]. 大地构造与成矿学, 2021, 45(6): 1146-1160.
[44]	陈伟林, 肖凡. 成矿动力学数值计算模拟研究进展: 理论、方法与技术[J]. 地质科技通报, 2023, 42(3): 234-249.
[45]	赵义来, 刘亮明. 复杂形态岩体接触带成矿耦合动力学三维数值模拟: 以安庆铜矿为例[J]. 大地构造与成矿学, 2011, 35(1): 128-136.
[46]	孙涛. 计算模拟用于研究与斑岩有关矿床的复杂性: 以大王顶金矿和车户沟钼铜矿为例[D]. 长沙: 中南大学, 2014.
[47]	HU X Y, LI X H, YUAN F, et al. 3D numerical simulation-based targeting of skarn type mineralization within the Xuancheng-magushan orefield, middle-Lower Yangtze metallogenic belt, China[J]. Lithosphere, 2020, 2020(1): 8351536.
[48]	周永章, 左仁广, 刘刚, 等. 数学地球科学跨越发展的十年: 大数据、人工智能算法正在改变地质学[J]. 矿物岩石地球化学通报, 2021, 40(3): 556-573.
[49]	刘艳鹏, 朱立新, 周永章. 卷积神经网络及其在矿床找矿预测中的应用: 以安徽省兆吉口铅锌矿床为例[J]. 岩石学报, 2018, 34(11): 3217-3224.
[50]	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.
[51]	ZUO R G, XIONG Y H, WANG J, et al. Deep learning and its application in geochemical mapping[J]. Earth-Science Reviews, 2019, 192: 1-14. DOI
[52]	袁传新, 贾东宁, 周生辉. 卷积神经网络在矿区预测中的研究与应用[J]. 工程科学学报, 2020, 42(12): 1597-1604.
[53]	LI H, LI XH, 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.
[1]	翟裕生, 邓军, 王建平, 等. 深部找矿研究问题[J]. 矿床地质, 2004, 23(2): 142-149.
[2]	叶天竺, 薛建玲. 金属矿床深部找矿中的地质研究[J]. 中国地质, 2007, 34(5): 855-869.
[3]	滕吉文. 强化开展地壳内部第二深度空间金属矿产资源地球物理找矿、勘探和开发[J]. 地质通报, 2006, 25(7): 767-771.
[4]	赵鹏大. 成矿定量预测与深部找矿[J]. 地学前缘, 2007, 14(5): 1-10.
[5]	SALAMA W, ANAND R R, VERRALL M. Mineral exploration and basement mapping in areas of deep transported cover using indicator heavy minerals and paleoredox fronts, Yilgarn Craton, Western Australia[J]. Ore Geology Reviews, 2016, 72(P1): 485-509.
[6]	吕庆田, 孟贵祥, 严加永, 等. 成矿系统的多尺度探测: 概念与进展: 以长江中下游成矿带为例[J]. 中国地质, 2019, 46(4): 673-689.
[7]	毛先成. 三维数字矿床与隐伏矿体立体定量预测研究[D]. 长沙: 中南大学, 2006.
[8]	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.
[9]	陈建平, 吕鹏, 吴文, 等. 基于三维可视化技术的隐伏矿体预测[J]. 地学前缘, 2007, 14(5): 54-62.
[54]	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.
[55]	WANG J, ZHOU Y Z, XIAO F. Identification of multi-element geochemical anomalies using unsupervised machine learning algorithms: a case study from Ag-Pb-Zn deposits in north-western Zhejiang, China[J]. Applied Geochemistry, 2020, 120: 104679.
[56]	LUO Z J, XIONG Y H, ZUO R G. Recognition of geochemical anomalies using a deep variational autoencoder network[J]. Applied Geochemistry, 2020, 122: 104710.
[57]	ZHOU S G, ZHOU K F, WANG J L. Geochemical metallogenic potential based on cluster analysis: a new method to extract valuable information for mineral exploration from geochemical data[J]. Applied Geochemistry, 2020, 122: 104748.
[58]	周永章, 王俊, 左仁广, 等. 地质领域机器学习、深度学习及实现语言[J]. 岩石学报, 2018, 34(11): 3173-3178.
[59]	JIN D, XU J, ZHAO K, et al. Attention-based 3D convolutional network for Alzheimer’s disease diagnosis and biomarkers exploration[C]// 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). Venice: IEEE, 2019: 1047-1051.
[60]	SHIM E, KIM J Y, YOON J P, et al. Automated rotator cuff tear classification using 3D convolutional neural network[J]. Scientific Reports, 2020, 10(1): 15632. DOI PMID
[61]	DOU Q, CHEN H, YU L Q, et al. Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks[J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1182-1195. DOI PMID
[62]	KAMNITSAS K, LEDIG C, NEWCOMBE V F J, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation[J]. Medical Image Analysis, 2017, 36: 61-78. DOI PMID
[63]	AHMAD A B, TSUJI T. Machine learning for automatic slump identification from 3D seismic data at convergent plate margins[J]. Marine and Petroleum Geology, 2021, 133: 105290.
[64]	LIU Y M, DURLOFSKY L J. 3D CNN-PCA: a deep-learning-based parameterization for complex geomodels[J]. Computers and Geosciences, 2021, 148: 104676.
[65]	GUO J T, LI Y Q, JESSELL M W, et al. 3D geological structure inversion from Noddy-generated magnetic data using deep learning methods[J]. Computers and Geosciences, 2021, 149: 104701.
[66]	LI S, CHEN J P, LIU C, et al. Mineral prospectivity prediction via convolutional neural networks based on geological big data[J]. Journal of Earth Science, 2021, 32(2): 327-347.
[67]	赵鹏大, 池顺都, 陈永清. 查明地质异常: 成矿预测的基础[J]. 高校地质学报, 1996, 2(4): 361-373.
[68]	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
[69]	CARRANZA E J M, WOLDAI T, CHIKAMBWE E M. Application of data-driven evidential belief functions to prospectivity mapping for aquamarine-bearing pegmatites, lundazi district, Zambia[J]. Natural Resources Research, 2005, 14(1): 47-63.
[70]	PORWAL A K, KREUZER O P. Introduction to the special issue: mineral prospectivity analysis and quantitative resource estimation[J]. Ore Geology Reviews, 2010, 38(3): 121-127.
[71]	LISITSIN V A, PORWAL A, MCCUAIG T C. Probabilistic fuzzy logic modeling: quantifying uncertainty of mineral prospectivity models using Monte Carlo simulations[J]. Mathematical Geosciences, 2014, 46(6): 747-769.
[72]	ZUO R G, WANG J, XIONG Y H, et al. The processing methods of geochemical exploration data: past, present, and future[J]. Applied Geochemistry, 2021, 132: 105072.
[73]	祁光, 吕庆田, 严加永, 等. 先验地质信息约束下的三维重磁反演建模研究: 以安徽泥河铁矿为例[J]. 地球物理学报, 2012, 55(12): 4194-4206.
[74]	丁文祥, 袁峰, 李晓晖, 等. 基于重磁联合反演的宁芜盆地钟姑矿田深部地质结构解析及成矿预测[J]. 地质学报, 2018, 92(11): 2301-2317.
[75]	丁文祥. 基于多源地学信息约束的繁昌盆地重磁联合反演及三维地质建模研究[D]. 合肥: 合肥工业大学, 2019.
[76]	LINDSAY M D, AILLÈRES L, JESSELL M W, et al. Locating and quantifying geological uncertainty in three-dimensional models: analysis of the Gippsland Basin, southeastern Australia[J]. Tectonophysics, 2012, 546: 10-27.
[77]	秦阳, 李晓晖, 唐敏惠, 等. 三维地质模型不确定性分析及对三维成矿预测结果的影响解析[J]. 大地构造与成矿学, 2023, 47(5): 1173-1182.
[78]	李晓晖, 戴文强, 袁峰, 等. 三维成矿预测数据整合过程不确定性研究: 以宁芜盆地钟姑矿田为例[J]. 岩石学报, 2018, 34(11): 3235-3243.
[79]	JIN X, WANG G W, TANG P, et al. 3D geological modelling and uncertainty analysis for 3D targeting in Shanggong gold deposit (China)[J]. Journal of Geochemical Exploration, 2020, 210: 106442.
[80]	孔维豪, 肖克炎, 陈建平, 等. 降低矿产资源定量预测不确定性的双向预测方法[J]. 地学前缘, 2021, 28(3): 128-138. DOI
[81]	王春女, 陈建平, 韩振哲, 等. 矿产预测中的不确定性评估方法与应用: 以赣北冷水坑矿区为例[J]. 中国矿业, 2015, 24(5): 142-148.
[82]	陈毓川. 中国主要成矿区带矿产资源远景评价[M]. 北京: 地质出版社, 1999.
[83]	曹新志, 张旺生, 孙华山. 我国深部找矿研究进展综述[J]. 地质科技情报, 2009, 28(2): 104-109.
[84]	郭镜, 李文昌, 李光明, 等. 多尺度综合地球物理方法在扎西康铅锌锑金多金属矿找矿预测中的应用[J]. 地球科学, 2019, 44(6): 2129-2142.
[85]	吕庆田, 董树文, 汤井田, 等. 多尺度综合地球物理探测: 揭示成矿系统、助力深部找矿: 长江中下游深部探测(SinoProbe-03)进展[J]. 地球物理学报, 2015, 58(12): 4319-4343. DOI
[86]	吕庆田, 张晓培, 汤井田, 等. 金属矿地球物理勘探技术与设备: 回顾与进展[J]. 地球物理学报, 2019, 62(10): 3629-3664. DOI
[87]	周文月, 严加永, 陈昌昕. 多尺度地球物理与成矿系统探测: 现状与进展[J]. 地球物理学进展, 2021, 36(3): 1208-1225.
[88]	郑小杰, 李晓晖, 袁峰, 等. 姚家岭锌金多金属矿床三维地质建模与成矿预测[J]. 地质科学, 2022, 57(3): 910-923.
[89]	MENG F D, LI X H, CHEN Y H, et al. Three-dimensional mineral prospectivity modeling for delineation of deep-seated skarn-type mineralization in Xuancheng-Magushan Area, China[J]. Minerals, 2022, 12: 1174.
[90]	LU S M, XUE Y L, LI L Z, et al. A 3D investigation of geological structure and its relationship to mineralization in the Nanling-Xuancheng ore district, middle-lower Yangtze River metallogenic belt, China[J]. Journal of Earth Science, 2022, 33(3): 664-680.
[91]	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.
[92]	周永章, 陈川, 张旗, 等. 地质大数据分析的若干工具与应用[J]. 大地构造与成矿学, 2020, 44(2): 173-182.