• 中国出版政府奖提名奖

    中国百强科技报刊

    湖北出版政府奖

    中国高校百佳科技期刊

    中国最美期刊

    留言板

    尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

    姓名
    邮箱
    手机号码
    标题
    留言内容
    验证码

    基于机器学习的华南诸广山花岗岩体铀矿潜力评价

    黄鑫怀 李增华 邓腾 刘志锋 陈冠群 曾皓轩 郭世超

    黄鑫怀, 李增华, 邓腾, 刘志锋, 陈冠群, 曾皓轩, 郭世超, 2023. 基于机器学习的华南诸广山花岗岩体铀矿潜力评价. 地球科学, 48(12): 4427-4440. doi: 10.3799/dqkx.2022.006
    引用本文: 黄鑫怀, 李增华, 邓腾, 刘志锋, 陈冠群, 曾皓轩, 郭世超, 2023. 基于机器学习的华南诸广山花岗岩体铀矿潜力评价. 地球科学, 48(12): 4427-4440. doi: 10.3799/dqkx.2022.006
    Huang Xinhuai, Li Zenghua, Deng Teng, Liu Zhifeng, Chen Guanqun, Zeng Haoxuan, Guo Shichao, 2023. Uranium Potential Evaluation of Zhuguangshan Granitic Pluton in South China Based on Machine Learning. Earth Science, 48(12): 4427-4440. doi: 10.3799/dqkx.2022.006
    Citation: Huang Xinhuai, Li Zenghua, Deng Teng, Liu Zhifeng, Chen Guanqun, Zeng Haoxuan, Guo Shichao, 2023. Uranium Potential Evaluation of Zhuguangshan Granitic Pluton in South China Based on Machine Learning. Earth Science, 48(12): 4427-4440. doi: 10.3799/dqkx.2022.006

    基于机器学习的华南诸广山花岗岩体铀矿潜力评价

    doi: 10.3799/dqkx.2022.006
    基金项目: 

    东华理工大学江西省放射性地学大数据技术工程实验室开放基金 JELRGBDT202006

    详细信息
      作者简介:

      黄鑫怀(1995-),男,硕士研究生,研究方向为铀矿地质.ORCID:0000-0001-5511-4054. E-mail:huangxinhuai2020@163.com

      通讯作者:

      李增华, 教授, 从事铀矿地质研究.ORCID: 0000-0003-2420-668X. E-mail: lizenghua@ecut.edu.cn

    • 中图分类号: P628;P595

    Uranium Potential Evaluation of Zhuguangshan Granitic Pluton in South China Based on Machine Learning

    • 摘要: 地学大数据和机器学习的结合,为矿床勘查提供了新的发展方向.华南广泛发育花岗岩体,是花岗岩型铀矿的重要产区,因此如何判断特定花岗岩体是否具有产铀矿的潜力,对于指导华南花岗岩型铀矿勘查具有重要意义.系统收集了前人已发表的华南花岗岩地球化学元素含量数据(不包括待评价的诸广山地区的九峰岩体、红山岩体和茶山岩体),共获得1 711条数据.然后按照7∶3的比例划分为训练集和测试集,进而分别建立了随机森林(random forest,RF)算法和K近邻(K-nearest neighbor,KNN)算法分类模型,并对两种分类模型的精确度、召回率、ROC(receiver operating characteristic curve)曲线进行评价,选出泛化能力较好的模型,最后利用泛化能力较好的模型对诸广山地区九峰岩体、红山岩体和茶山岩体进行成矿潜力评价.结果表明,随机森林分类模型对测试集的分类精确度、预测结果可靠度均高于K近邻分类模型,随机森林分类模型对测试集上的数据分类精确度达到了93%,利用上述创建的随机森林分类模型对九峰、红山和茶山岩体进行预测.预测结果表明,红山岩体和茶山岩体含矿的概率较高,而九峰岩体含矿概率较低.该研究为进一步缩小地质找矿勘查范围提供了可靠的依据,并且该模型可以作为地质找矿工作者的辅助工具.

       

    • 图  1  诸广山岩体分布及采样点位置图

      1.中粒-细粒二云母花岗岩;2.中-中粗粒(斑状)黑云母花岗岩;3.粗粒斑状黑云母花岗岩;4.印支期花岗岩;5.海西期黑云母闪长岩;6.加里东期花岗闪长岩;7.条带状混合花岗岩;8.条带状混合岩;9.取样点及编号;10.铀矿床及编号;11.断裂;图改自朱捌(2010)

      Fig.  1.  Zhuguangshan pluton distribution and sampling point location map

      图  2  花岗岩主量元素槽口箱线图

      Fig.  2.  Box diagram of granite major element slot

      图  3  花岗岩微量元素槽口箱线图

      Fig.  3.  Box diagram of granite trace element slot

      图  4  基于随机森林模型的重要性度量

      Fig.  4.  Importance measurement based on random forest model

      图  5  随机森林模型max_feature选取图

      Fig.  5.  Max_feature selection diagram of random forest model

      图  6  随机森林模型n_estimators选取图

      Fig.  6.  Random forest model n_estimators selection diagram

      图  7  随机森林分类模型混淆矩阵图

      Fig.  7.  Random forest classification model confusion matrix diagram

      图  8  KNN近邻数选取图

      Fig.  8.  K value selection graph of KNN algorithm

      图  9  KNN分类模型混淆矩阵图

      Fig.  9.  KNN classification model confusion matrix diagram

      图  10  准确率-召回率曲线

      Fig.  10.  Accuracy-recall curve

      图  11  ROC曲线

      Fig.  11.  ROC curve

      表  1  九峰、红山和茶山岩体随机森林模型预测结果

      Table  1.   Jiufeng, Hongshan and Chashan plutons random forest model prediction results

      编号 不含矿概率(%) 含矿概率(%) 预测结果
      九峰岩体 06168 64 36 0
      06170 86 14 0
      06171 89 11 0
      06172 93 7 0
      06173 84 16 0
      0629 17 83 1
      红山岩体 0631 11 89 1
      0632 10 90 1
      0633 10 90 1
      0635 9 91 1
      06184 4 96 1
      茶山岩体 06185 3 97 1
      06186 1 99 1
      下载: 导出CSV
    • 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
      Breiman, L., 2001. Random Forest. Machine Learning, 45: 5-32. doi: 10.1023/A:1010933404324
      Breiman, L., 2004. RFtools-for Predicting and Understanding Data. Technical Report, Berkeley University, Berkeley, USA.
      Brown, W.M., Groves, D.I., Gedeon, T.D., 2003. An Artificial Neural Network Method for Mineral Prospectivity Mapping: A Comparison with Fuzzy Logic and Bayesian Probability Methods. In: Sandham, W.A., Leggett, M., eds., Geophysical Applications of Artificial Neural Networks and Fuzzy Logic. Modern Approaches in Geophysics, 21. Springer, Dordrecht. https://doi.org/10.1007/978-94-017-0271-3_12
      Chehreh Chelgani, S., Matin, S.S., Hower, J.C., 2016. Explaining Relationships between Coke Quality Index and Coal Properties by Random Forest Method. Fuel, 182: 754-760. https://doi.org/10.1016/j.fuel.2016.06.034
      Chen, Y.L., Zhou, B., Li, X.B., 2012. Mineral Target Prediction Based on Boltzmann Machines. Progress in Geophysics, 27(1): 179-185(in Chinese with English abstract).
      Dong, S.S., Huang, Z.X., 2013. A Brief Theoretical Overview of Random Forests. Journal of Integration Technology, 2(1): 1-7(in Chinese with English abstract).
      Hao, H.Z., Gu, Q., Hu, X.M., 2021. Research Advances and Prospective in Mineral Intelligent Identification Based on Machine Learning. Earth Science, 46(9): 3091-3106(in Chinese with English abstract).
      Harris, D., Zurcher, L., Stanley, M., et al., 2003. A Comparative Analysis of Favorability Mappings by Weights of Evidence, Probabilistic Neural Networks, Discriminant Analysis, and Logistic Regression. Natural Resources Research, 12(4): 241-255. https://doi.org/10.1023/b:narr.0000007804.27450.e8
      Hong, J., Gan, C.S., Liu, J., 2018. Preliminary Study on the Relationship between Trace and Major Elements in Rocks Based on Machine Learning: A Case Study of Zr in OIB. Chinese Journal of Geology, 53(4): 1285-1299(in Chinese with English abstract).
      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
      Izadi, H., Sadri, J., Mehran, N.A., 2013. Intelligent Mineral Identification Using Clustering and Artificial Neural Networks Techniques. 2013 First Iranian Conference on Pattern Recognition and Image Analysis (PRIA), IEEE. Birjand, Iran. https://doi.org/10.1109/pria.2013.6528426
      Lan, H.F., Wang, H.Z., Ling, H.F., et al., 2020. Petrogenesis of the Chashan Granite in the Northern Guangdong Province and Its Implication for the Metallogenic Potential of Tungsten and Uranium Mineralization. Acta Geologica Sinica, 94(4): 1143-1165(in Chinese with English abstract). doi: 10.3969/j.issn.0001-5717.2020.04.009
      Matin, S.S., Chelgani, S.C., 2016. Estimation of Coal Gross Calorific Value Based on Various Analyses by Random Forest Method. Fuel, 177: 274-278. https://doi.org/10.1016/j.fuel.2016.03.031
      Nicodemus, K.K., Malley, J.D., 2009. Predictor Correlation Impacts Machine Learning Algorithms: Implications for Genomic Studies. Bioinformatics, 25(15): 1884-1890. https://doi.org/10.1093/bioinformatics/btp331
      Rodriguez-Galiano, V., Sanchez-Castillo, M., Chica-Olmo, M., et al., 2015. Machine Learning Predictive Models for Mineral Prospectivity: An Evaluation of Neural Networks, Random Forest, Regression Trees and Support Vector Machines. Ore Geology Reviews, 71: 804-818. https://doi.org/10.1016/j.oregeorev.2015.01.001
      Shao, F., Xu, J.J., Shao, S., et al., 2014. Geological Characteristics and Mineralization of the Granite-Type Uranium Deposits in South China. Resources Survey and Environment, 35(3): 211-217(in Chinese with English abstract).
      Song, Y., Huang, J., Zhou, D., et al., 2007. IKNN: Informative K-Nearest Neighbor Pattern Classification. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., eds., Knowledge Discovery in Databases: PKDD 2007, PKDD 2007. Lecture Notes in Computer Science, 4702. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74976-9_25
      Strobl, C., Boulesteix, A.L., Kneib, T., et al., 2008. Conditional Variable Importance for Random Forests. BMC Bioinformatics, 9: 307. https://doi.org/10.1186/1471-2105-9-307
      Sun, Z.Y., Liu, H.Y., Ju, H.Y., et al., 2021. Assessment of Importance-Based Machine Learning Feature Selection Methods for Aggregate Size Distribution Measurement in a 3D Binocular Vision System. Construction and Building Materials, 306: 124894. https://doi.org/10.1016/j.conbuildmat.2021.124894
      Tian, Z.J., 2014. Comparative Study on Chronology, Geochemistry and Mineralogical Characteristics of Uranium-Producing and Uranium-Non-Producing Granites in Zhiguang Mountain (Dissertation). China University of Geosciences, Beijing(in Chinese with English abstract).
      Vincenzi, S., Zucchetta, M., Franzoi, P., et al., 2011. Application of a Random Forest Algorithm to Predict Spatial Distribution of the Potential Yield of Ruditapes Philippinarum in the Venice Lagoon, Italy. Ecological Modelling, 222(8): 1471-1478. https://doi.org/10.1016/j.ecolmodel.2011.02.007
      Wang, H.Z., Yang, F., Luo, Z.Y., 2016. An Experimental Study of the Intrinsic Stability of Random Forest Variable Importance Measures. BMC Bioinformatics, 17: 60. https://doi.org/10.1186/s12859-016-0900-5
      Wang, K.X., Sun, T., Yu, J.H., et al., 2020. Provenances of the Ediacaran Sedimentary Rocks in the Zhuguangshan Area and Their Implications for Granitoid-Related Uranium Mineralization in South China. Ore Geology Reviews, 124: 103588. https://doi.org/10.1016/j.oregeorev.2020.103588
      Wu, H., Xia, Y., Zhou, K.K., et al., 2020. Highly Fractionated Granite Magmas maybe the Main Uranium Source of Granite-Type Uranium Deposits in South China: Evidence from the Uranium Content of Zircon in Southern Zhuguangshan Granitic Composite. Acta Petrologica Sinica, 36(2): 589-600 (in Chinese with English abstract). doi: 10.18654/1000-0569/2020.02.16
      Xiao, Z.H., Xiong, S.B., Li, C.H., et al., 2020. Types of Uranium Deposits in Central Zhuguang Mountains in Hunan Province, South China and Their Metallogenic Regularity and Prospecting Directions. China Geology, 3(3): 411-424. https://doi.org/10.31035/cg2020040
      Yin, X.Z., 2009. An Ameliorated SVM Classifying Algorithm Combined with KNN. Journal of Image and Graphics, 14(11): 2299-2303(in Chinese with English abstract). doi: 10.11834/jig.20091117
      Youn, E., Jeong, M.K., 2009. Class Dependent Feature Scaling Method Using Naive Bayes Classifier for Text Datamining. Pattern Recognition Letters, 30(5): 477-485. https://doi.org/10.1016/j.patrec.2008.11.013
      Zhang, B.Y., Sun, J.K., Luo, X., et al., 2019. Data Analysis of Major and Trace Element of Gabbro Clinopyroxene from Different Tectonic Setting. Earth Science Frontiers, 26(4): 33-44(in Chinese with English abstract).
      Zhang, L., 2017. Mineralogical Characteristics of Representative Yanshanian Granites in Southern Zhuguang and Their Implications for Petrogenesis and Metallogenic Potential (Dissertation). Nanjing University, Nanjing(in Chinese with English abstract).
      Zhang, L., Chen, Z.Y., Li, S.R., et al., 2017. Isotope Geochronology, Geochemistry, and Mineral Chemistry of the U-Bearing and Barren Granites from the Zhuguangshan Complex, South China: Implications for Petrogenesis and Uranium Mineralization. Ore Geology Reviews, 91: 1040-1065. https://doi.org/10.1016/j.oregeorev.2017.07.017
      Zhang, L., Chen, Z.Y., Li, X.F., et al., 2018. Zircon U-Pb Geochronology and Geochemistry of Granites in the Zhuguangshan Complex, South China: Implications for Uranium Mineralization. Lithos, 308-309: 19-33. https://doi.org/10.1016/j.lithos.2018.02.029
      Zhang, Q., Zhou, Y.Z., 2017. Big Data will Lead to a Profound Revolution in the Field of Geological Science. Chinese Journal of Geology, 52(3): 637-648(in Chinese with English abstract).
      Zheng, Z.Y., 2019. Comparison of Several Machine Learning Methods for Identification of Multiple Geochemical Anomalies in Helong Area, Jilin Province (Dissertation). Jilin University, Changchun (in Chinese with English abstract).
      Zhou, Y.Z., Chen, S., Zhang, Q., et al., 2018a. Advances and Prospects of Big Data and Mathematical Geoscience. Acta Petrologica Sinica, 34(2): 255-263(in Chinese with English abstract).
      Zhou, Y.Z., Wang, J., Zuo, R.G., et al., 2018b. Machine Learning, Deep Learning and Python Language in Field of Geology. Acta Petrologica Sinica, 34(11): 3173-3178(in Chinese with English abstract).
      Zhou, Y.Z., Li, P.X., Wang, S.G., et al., 2017. Research Progress on Big Data and Intelligent Modelling of Mineral Deposits. Bulletin of Mineralogy, Petrology and Geochemistry, 36(2): 327-331, 344 (in Chinese with English abstract). doi: 10.3969/j.issn.1007-2802.2017.02.016
      Zhou, Y.Z., Zuo, R.G., Liu, G., et al., 2021. The Great-Leap-Forward Development of Mathematical Geoscience during 2010—2019: Big Data and Artificial Intelligence Algorithm are Changing Mathematical Geoscience. Bulletin of Mineralogy, Petrology and Geochemistry, 40(3): 556-573, 777(in Chinese with English abstract).
      Zhu, B., 2010. Research on Mantle Fluid and Uranium Mineralization (Dissertation). Chengdu University of Technology, Chengdu(in Chinese with English abstract).
      Zuo, R.G., Peng, Y., Li, T., et al., 2021. Challenges of Geological Prospecting Big Data Mining and Integration Using Deep Learning Algorithms. Earth Science, 46(1): 350-358(in Chinese with English abstract).
      陈永良, 周斌, 李学斌, 2012. 基于Boltzmann机的矿产靶区预测. 地球物理学进展, 27(1): 179-185.
      董师师, 黄哲学, 2013. 随机森林理论浅析. 集成技术, 2(1): 1-7.
      郝慧珍, 顾庆, 胡修棉, 2021. 基于机器学习的矿物智能识别方法研究进展与展望. 地球科学, 46(9): 3091-3106. doi: 10.3799/dqkx.2020.360
      洪瑾, 甘成势, 刘洁, 2018. 基于机器学习的岩石微量元素与主量元素关系初探: 以洋岛玄武岩中锆元素为例. 地质科学, 53(4): 1285-1299.
      兰鸿锋, 王洪作, 凌洪飞, 等, 2020. 粤北茶山岩体岩石成因与铀、钨成矿潜力探讨. 地质学报, 94(4): 1143-1165. doi: 10.3969/j.issn.0001-5717.2020.04.009
      邵飞, 许健俊, 邵上, 等, 2014. 华南花岗岩型铀矿地质特征及成矿作用. 资源调查与环境, 35(3): 211-217. doi: 10.3969/j.issn.1671-4814.2014.03.009
      田泽瑾, 2014. 诸广山产铀与不产铀花岗岩的年代学, 地球化学及矿物学特征对比研究(硕士学位论文). 北京: 中国地质大学.
      伍皓, 夏彧, 周恳恳, 等, 2020. 高分异花岗岩浆可能是华南花岗岩型铀矿床主要铀源: 来自诸广山南体花岗岩锆石铀含量的证据. 岩石学报, 36(2): 589-600.
      殷小舟, 2009. 一种改进的结合K近邻法的SVM分类算法. 中国图象图形学报, 14(11): 2299-2303. doi: 10.11834/jig.20091117
      郑泽宇, 2019. 吉林省和龙地区多元地球化学异常识别的几种机器学习方法比较(硕士学位论文). 长春: 吉林大学.
      章宝月, 孙建鹍, 罗熊, 等, 2019. 三类构造背景辉长岩单斜辉石主量元素和微量元素的数据分析研究. 地学前缘, 26(4): 33-44.
      张丽, 2017. 诸广南部燕山期代表性花岗岩的矿物学特征及对岩石成因和成矿潜力的指示意义(硕士学位论文). 南京: 南京大学.
      张旗, 周永章, 2017. 大数据正在引发地球科学领域一场深刻的革命: 《地质科学》2017年大数据专题代序. 地质科学, 52(3): 637-648.
      周永章, 陈烁, 张旗, 等, 2018a. 大数据与数学地球科学研究进展: 大数据与数学地球科学专题代序. 岩石学报, 34(2): 255-263.
      周永章, 王俊, 左仁广, 等, 2018b. 地质领域机器学习、深度学习及实现语言. 岩石学报, 34(11): 3173-3178.
      周永章, 黎培兴, 王树功, 等, 2017. 矿床大数据及智能矿床模型研究背景与进展. 矿物岩石地球化学通报, 36(2): 327-331, 344.
      周永章, 左仁广, 刘刚, 等, 2021. 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. 矿物岩石地球化学通报, 40(3): 556-573, 777.
      朱捌, 2010. 地幔流体与铀成矿作用研究(博士学位论文). 成都: 成都理工大学.
      左仁广, 彭勇, 李童, 等, 2021. 基于深度学习的地质找矿大数据挖掘与集成的挑战. 地球科学, 46(1): 350-358. doi: 10.3799/dqkx.2020.111
    • 加载中
    图(11) / 表(1)
    计量
    • 文章访问数:  808
    • HTML全文浏览量:  536
    • PDF下载量:  85
    • 被引次数: 0
    出版历程
    • 收稿日期:  2021-12-11
    • 网络出版日期:  2024-01-03
    • 刊出日期:  2023-12-25

    目录

      /

      返回文章
      返回