基于机器学习的贵州省萤石矿稀土元素判别模型
吕代和 , 田倩 , 刘雨 , 刘刚 , 周琦 , 祁连素
地球科学 ›› 2026, Vol. 51 ›› Issue (03) : 1093 -1109.
基于机器学习的贵州省萤石矿稀土元素判别模型
Machine Learning-Based Discrimination Model for Rare Earth Elements of Fluorite Deposits in Guizhou Province
贵州西部萤石矿集区内新识别出的隐爆角砾岩型萤石矿具有巨大的找矿潜力.然而该类型萤石矿角砾状构造、热液蚀变等特征易与其他热液角砾岩型矿床或强烈构造改造的脉型矿床相混淆,如何准确识别研究区内隐爆角砾岩型和与盆地卤水相关热液填充型萤石矿是实现贵州省萤石矿找矿突破的关键科学问题之一.本文通过对系统收集的隐爆角砾岩型、与岩浆热液相关的热液充填型和与盆地卤水相关热液填充型三种成因类型萤石矿的稀土元素数据进行支持向量机和随机森林机器学习分类模型对比研究,并结合基于主成分分析的统计分析、降维可视化和稀土元素分离度评分体系定量评估进行综合研究.结果显示支持向量机构建的判别模型准确率与稳定性均显著优于随机森林,可以更加有效地判别这三种成因类型萤石矿,并识别出可用于区分三种成因类型萤石矿的关键元素精炼候选池,构建出了新的Tb/Dy-Sm/Yb、δCe-Sm/Yb、δCe-Sm/Tm、δEu-Sm/Lu判别图,后续实验也验证了该方法可以有效区分隐爆角砾岩型、与岩浆热液相关的热液充填型和与盆地卤水相关热液填充型萤石矿.
The newly identified cryptic explosive breccia-type fluorite deposits in the western Guizhou fluorite ore concentration area possess significant prospecting potential. However, the brecciated textures, hydrothermal alteration, and other characteristics of this type of fluorite deposit are easily confused with those of other hydrothermal breccia-type deposits or intensely structurally altered vein-type deposits. Therefore, accurately distinguishing between cryptic explosive breccia-type fluorite deposits and basin brine-related hydrothermal filling-type fluorite deposits in the study area is one of the key scientific challenges for achieving breakthroughs in fluorite prospecting in Guizhou Province. This paper conducts a comparative study of Support Vector Machine (SVM) and Random Forest machine learning classification models using systematically collected rare earth element (REE) data from three genetic types of fluorite deposits: cryptic explosive breccia-type, magmatic hydrothermal-related filling-type, and basin brine-related hydrothermal filling-type, which is combined with comprehensive analysis, including statistical analysis based on Principal Component Analysis (PCA), dimensionality reduction visualization, and quantitative evaluation using an REE separation scoring system. The results indicate that the discriminant model constructed by SVM exhibits significantly higher accuracy and stability compared to Random Forest, enabling more effective discrimination among these three genetic types of fluorite deposits. Furthermore, it identifies a refined candidate pool of key elements that can be used to distinguish them. Newly constructed discriminant diagrams (Tb/Dy vs Sm/Yb, δCe vs Sm/Yb, δCe vs Sm/Tm, δEu vs Sm/Lu) have been developed, which effectively differentiate among cryptic explosive breccia-type, magmatic hydrothermal-related hydrothermal filling-type, and basin brine-related hydrothermal filling-type fluorite deposits.
| [1] |
Altmann, A., Toloşi, L., Sander, O., et al., 2010. Permutation Importance: A Corrected Feature Importance Measure. Bioinformatics, 26(10): 1340-1347. https://doi.org/10.1093/bioinformatics/btq134 |
| [2] |
Bai, Y., 2020. Geological Characteristics and Structural Ore⁃Control Regularity of Fluorite Deposits in Northern Siziwang Banner, Inner Mongolia (Dissertation). China University of Geosciences, Beijing (in Chinese with English abstract). |
| [3] |
Bau, M., Dulski, P., 1995. Comparative Study of Yttrium and Rare⁃Earth Element Behaviours in Fluorine⁃Rich Hydrothermal Fluids. Contributions to Mineralogy and Petrology, 119(2): 213-223. https://doi.org/10.1007/BF00307282 |
| [4] |
Bau, M., Möller, P., 1992. Rare Earth Element Fractionation in Metamorphogenic Hydrothermal Calcite, Magnesite and Siderite. Mineralogy and Petrology, 45(3): 231-246. https://doi.org/10.1007/BF01163114 |
| [5] |
Breiman, L., 2001. Random Forests. Machine Learning, 45(1): 5-32. https://doi.org/10.1023/A:1010933404324 |
| [6] |
Boynton, W. V., 1984. Cosmochemistry of the Rare Earth Elements: Meteorite Studies. Elsevier, Amsterdam. https://doi.org/10.1016/b978⁃0⁃444⁃42148⁃7.50008⁃3 |
| [7] |
Cai, H. J., Zhang, B. G., Li, Y. S., 1996. REE Geochemistry of Fluorite in Stibnite⁃Fluorite Paragenetic Deposits. Geology⁃Geochemistry, 24(2): 103-106 (in Chinese with English abstract). |
| [8] |
Carniel, R., Guzmán, S. R., 2021. Machine Learning in Volcanology: A Review. In: Németh, K., ed., Updates in Volcanology: Transdisciplinary Nature of Volcano Science. IntechOpen, London. https://doi.org/10.5772/intechopen.94217 |
| [9] |
Chen, D., Liu, Z. C., Tang, Z. C., et al., 2023. Rare Earth Element Geochemical Characteristics of Fluorite Deposits in Fuyang Area, Wuchuan, Guizhou Province. Acta Mineralogica Sinica, 43(6): 861-872 (in Chinese with English abstract). |
| [10] |
Cortes, C., Vapnik, V., 1995. Support⁃Vector Networks. Machine Learning, 20(3): 273-297. https://doi.org/10.1023/A:1022627411411 |
| [11] |
Guo, Y., Chen, D., Tang, Z. C., et al., 2023. Ceochemical Characteristics of Rare Earth Elements and the Source of Ore⁃Forming Materials in the Jinliang Fluorite Deposit in the Northeastern Guizhou. Acta Mineralogica Sinica, 43(6): 873-881 (in Chinese with English abstract). |
| [12] |
Hong, S., Zuo, R. G., Huang, X. W., et al., 2021. Distinguishing IOCG and IOA Deposits via Random Forest Algorithm Based on Magnetite Composition. Journal of Geochemical Exploration, 230: 106859. https://doi.org/10.1016/j.gexplo.2021.106859 |
| [13] |
Hou, L. L., Wu, S., Yi, J. Z., et al., 2024. Discriminating Deposit Types Using Chlorite Trace Elements Based on Machine Learning. Earth Science, 49(12): 4303-4317 (in Chinese with English abstract). |
| [14] |
Hu, B., Zeng, L. P., Liao, W., et al., 2022. The Origin and Discrimination of High⁃Ti Magnetite in Magmatic⁃Hydrothermal Systems: Insight from Machine Learning Analysis. Economic Geology, 117(7): 1613-1627. https://doi.org/10.5382/econgeo.4946 |
| [15] |
Huang, X. W., Boutroy, É., Makvandi, S., et al., 2019. Trace Element Composition of Iron Oxides from IOCG and IOA Deposits: Relationship to Hydrothermal Alteration and Deposit Subtypes. Mineralium Deposita, 54(4): 525-552. https://doi.org/10.1007/s00126⁃018⁃0825⁃1 |
| [16] |
Jin, S. R., Chen, J., Dai, D. R., et al., 2018. Geochemical Characteristics of Trace Elements and REE in the Gaoling Fluorite Deposit, Southwest Guizhou, China. Acta Mineralogica Sinica, 38(6): 684-692 (in Chinese with English abstract). |
| [17] |
Jolliffe, I. T., Cadima, J., 2016. Principal Component Analysis: A Review and Recent Developments. Philosophical Transactions Series A, Mathematical, Physical, and Engineering Sciences, 374(2065): 20150202. https://doi.org/10.1098/rsta.2015.0202 |
| [18] |
Lachaud, A., Adam, M., Mišković, I., 2023. Comparative Study of Random Forest and Support Vector Machine Algorithms in Mineral Prospectivity Mapping with Limited Training Data. Minerals, 13(8): 1073. https://doi.org/10.3390/min13081073 |
| [19] |
Li, M., 2022. Geological Characteristics and Genesis of the Shuanghe Barite⁃Fluorite Deposit in Northeastern Guizhou Province (Dissertation). Chengdu University of Technology, Chengdu (in Chinese with English abstract). |
| [20] |
Liu, D. R., Shang, P. Q., 2023. Classification and REE Geochemical Characteristics of Fluorite Deposits in China. Geology and Exploration, 59(2): 211-222 (in Chinese with English abstract). |
| [21] |
Möller, P., Parekh, P. P., Schneider, H. J., 1976. The Application of Tb/Ca⁃Tb/La Abundance Ratios to Problems of Fluorspar Genesis. Mineralium Deposita, 11(1): 111-116. https://doi.org/10.1007/BF00203098 |
| [22] |
Peng, J. T., Hu, R. Z., Qi, L., et al., 2002. Ree Geochemistry of Fluorite from the Qinglong Antimony Deposit and Its Geological Implications. Scientia Geologica Sinica, 37(3): 277-287 (in Chinese with English abstract). |
| [23] |
Petrelli, M., Bizzarri, R., Morgavi, D., et al., 2017. Combining Machine Learning Techniques, Microanalyses and Large Geochemical Datasets for Tephrochronological Studies in Complex Volcanic Areas: New Age Constraints for the Pleistocene Magmatism of Central Italy. Quaternary Geochronology, 40: 33-44. https://doi.org/10.1016/j.quageo.2016.12.003 |
| [24] |
Qi, L. S., Yin, T. L., Huang, Q. L., et al., 2025. The Vapour⁃Fluid⁃Explosion Mineralization of the Heishanqing Fluorite Deposit in Qinglong County, Guizhou Province. Acta Mineralogica Sinica, 45(4): 823-834 (in Chinese with English abstract). |
| [25] |
Rao, H. J., Luo, P., Yang, Z. X., et al., 2010. Geochemistry of Fluorite and Its Genesis in Sickl Area, Tarim Basin. Acta Sedimentologica Sinica, 28(4): 821-831 (in Chinese with English abstract). |
| [26] |
Schwinn, G., Markl, G., 2005. REE Systematics in Hydrothermal Fluorite. Chemical Geology, 216(3/4): 225-248. https://doi.org/10.1016/j.chemgeo.2004.11.012 |
| [27] |
Shuai, Q. Y., Li, J. H., Wei, G. H., et al., 2025. Characteristics of Ore⁃Forming Fluids and Ore Genesis of the Yaojiata Fluorite Deposit in Southern Anhui: Constraints from Rare Earth Elements and Fluid Inclusions. Chinese Journal of Geology, 60(5): 1426-1439 (in Chinese with English abstract). |
| [28] |
Sun, S. S., McDonough, W. F., 1989. Chemical and Isotopic Systematics of Oceanic Basalts: Implications for Mantle Composition and Processes. Geological Society, London, Special Publications, 42(1): 313-345. https://doi.org/10.1144/gsl.sp.1989.042.01.19 |
| [29] |
U.S. Geological Survey, 2024. Mineral Commodity Summaries 2024. U.S. Geological Survey, Reston. https://doi.org/10.3133/mcs2024 |
| [30] |
Wang, J., 2019. Metallogenic Characteristics and Ore⁃Prospecting Prediction Research of the Dachang Ore Concentration Area in Qinglong, Guizhou Province (Dissertation). China University of Geosciences, Beijing (in Chinese with English abstract). |
| [31] |
Wang, J. P., Shang, P. Q., Xiong, X. X., et al., 2014. The Classification of Fluorite Deposits in China. Geology in China, 41(2): 315-325 (in Chinese with English abstract). |
| [32] |
Wang, K., 2022. Types and Geological⁃Geochemical Characteristics of Fluorite Deposits in the Southern Section of the Greater Khingan Range (Dissertation). China University of Geosciences, Beijing (in Chinese with English abstract). |
| [33] |
Wang, P., Glover, L., 1992. A Tectonics Test of the Most Commonly Used Geochemical Discriminant Diagrams and Patterns. Earth⁃Science Reviews, 33(2): 111-131. https://doi.org/10.1016/0012⁃8252(92)90022⁃L |
| [34] |
Xia, X. H., Han, Y. C., Lian, W., et al., 2009. Genesis Discussion and REE Geochemistry Characters in Ba⁃Mianshan Fluorite Deposit in Zhejiang Province. Geology of Chemical Minerals, 31(4): 193-200 (in Chinese with English abstract). |
| [35] |
Xu, Y. D., Qi, L. S., Yin, T. L., et al., 2023. Geochemical Characteristics of Trace Elements and Rare Earth Elements(REE) of the Donggualin Fluorite Deposit in Qinglong City, Guizhou Province. Acta Mineralogica Sinica, 43(6): 853-860 (in Chinese with English abstract). |
| [36] |
Yu, L. M., Zou, H., Santosh, M., et al., 2022. The Link between Paleo⁃Tethys Subduction and Regional Metallogeny in the SW Yangtze Block: New Evidence from the Zubu Carbonate⁃Hosted F⁃Pb⁃Zn Deposit. Ore Geology Reviews, 144: 104809. https://doi.org/10.1016/j.oregeorev.2022.104809 |
| [37] |
Zhang, H. F., Wen, J., Chen, M., et al., 2025. Sources of Ore⁃Forming Materials of Fluorite Deposit in the Mabian Area, Southwest Sichuan, and Implications for Regional Prospecting of Fluorite. Geological Bulletin of China, 44(10): 1816-1829 (in Chinese with English abstract). |
| [38] |
Zhang, X. Y., Gu, J. Y., Luo, P., et al., 2006. Genesis of the Fluorite in the Ordovician and Its Significance to the Petroleum Geology of Tarim Basin. Acta Petrologica Sinica, 22(8): 2220-2228 (in Chinese with English abstract). |
| [39] |
Zhang, Z. Z., Gong, Y. J., Chen, L. B., et al., 2018. Geochemical Evidence of the Source of Ore⁃Forming Materials from Dazhuyuan Fluorite Deposit in Northeastern Guizhou. Geochimica, 47(3): 295-305 (in Chinese with English abstract). |
| [40] |
Zhou, B. W., 2023. Geochemical Characteristics and Genesis Discussion of the Zhangcuo Fluorite Deposit in Shaowu, Fujian Province (Dissertation). Kunming University of Science and Technology, Kunming (in Chinese with English abstract). |
| [41] |
Zhou, Q., Tao, P., Chen, Q. F., et al., 2025. Metallogenic Regularity, Centennial Exploration Results of Guizhou Province, and Suggestions for a New Round of Prospecting: Research and Compilation of “Geology of Mineral Resources of China · Guizhou Volume”. Acta Geoscientica Sinica, 46(1): 172-183 (in Chinese with English abstract). |
| [42] |
Zhou, Z. H., Cao, W. G., Dai, Y. H., et al., 2024. Ore⁃Controlling Factors and Prospecting Direction of Fluorite Belt in Northeastern Lianhuashan Anticline, Southwestern Guizhou. Guizhou Geology, 41(3): 270-277 (in Chinese with English abstract). |
| [43] |
Zou, H., Dan, Y., Zhang, S. T., et al., 2016. Geochemical Evidence for Sources of Ore⁃Forming Material of Barite⁃Fluorite Deposits in Pengshui Area, Southeast Chongqing. Geotectonica et Metallogenia, 40(1): 71-85 (in Chinese with English abstract). |
| [44] |
Zou, H., Fang, Y., Chen, H. M., et al., 2014. REE Geochemistry and Genesis of the Xiachen Fluorite Deposit in Tiantai Basin, Zhejiang Province. Geology in China, 41(4): 1375-1386 (in Chinese with English abstract). |
| [45] |
Zou, H., Li, M., Santosh, M., et al., 2022. Fault⁃Controlled Carbonate⁃Hosted Barite⁃Fluorite Mineral Systems: The Shuanghe Deposit, Yangtze Block, South China. Gondwana Research, 101: 26-43. https://doi.org/10.1016/j.gr.2021.07.020 |
| [46] |
Zuo, R. G., Carranza, E. J. M., 2023. Machine Learning⁃Based Mapping for Mineral Exploration. Mathematical Geosciences, 55(7): 891-895. https://doi.org/10.1007/s11004⁃023⁃10097⁃3 |
| [47] |
Zuo, R. G., Yang, F. F., Cheng, Q. M., et al., 2025. A Novel Data⁃Knowledge Dual⁃Driven Model Coupling Artificial Intelligence with a Mineral Systems Approach for Mineral Prospectivity Mapping. Geology, 53(3): 284-288. https://doi.org/10.1130/g52970.1 |
贵州省重大科技专项(黔科合重大[2025]016)
贵州省科技创新人才团队建设项目(黔科合人才CXTD[2025]026)
贵州省科技计划项目(No.黔科合平台人才⁃ZDSYS[2023]005)
/
| 〈 |
|
〉 |