吉林大学学报(地球科学版) ›› 2021, Vol. 51 ›› Issue (3): 723-733.doi: 10.13278/j.cnki.jjuese.20200305
刘云鹏1,2,3, 郭春影1,2, 秦明宽1,2, 吴玉1,2, 裴柳宁1,2
Liu Yunpeng1,2,3, Guo Chunying1,2, Qin Mingkuan1,2, Wu Yu1,2, Pei Liuning1,2
摘要: 不同类型铀矿床的沥青铀矿/晶质铀矿具有不同的稀土元素组成,其组成可作为判别铀矿床类型的重要指标。采用基于Python语言的主成分分析(principal component analysis,PCA)与支持向量机(support vector machines,SVM)结合的分类模型,对收集到的全球已知6种类型铀矿床的216组沥青铀矿/晶质铀矿稀土元素数据进行研究。以216组数据为训练集,通过数据清洗、特征缩放、PCA特征提取、网格搜索和交叉验证参数寻优构建SVM分类模型,对24组同变质型胡家峪晶质铀矿进行智能识别。研究结果显示:仅使用稀土元素的14维训练集最优模型判定胡家峪晶质铀矿类型的测试准确率为0.4%;由稀土元素、稀土总量、轻重稀土比、铕异常组成的17维训练集最优模型的测试准确率为75.0%,较14维训练集提高74.6%,模型泛化能力强;而通过传统稀土元素配分曲线、w(ΣREE)-(LREE/HREE)N图解不能有效判定胡家峪晶质铀矿类型。本次研究表明,PCA-SVM算法对增有传统稀土判别指标数据集进行挖掘可有效厘定铀氧化物成因类型,效果明显优于单纯的稀土元素数据集以及传统的稀土配分曲线、w(ΣREE)-(LREE/HREE)N图解。
中图分类号:
[1] 韩帅,李明超,任秋兵,等. 基于大数据方法的玄武岩大地构造环境智能挖掘判别与分析[J].岩石学报,2018,34(11): 3207-3216. Han Shuai, Li Mingchao, Ren Qiubing, et al. Intelligent Determination and Data Mining for Tectonic Settings of Basalts Based on Big Data Methods[J]. Acta Petrologica Sinica, 2018, 34(11): 3207-3216. [2] 焦守涛,周永章,张琪,等. 基于GEOROC数据库的全球辉长岩大数据的大地构造环境智能判别研究[J]. 岩石学报,2018,34(11): 3189-3194. Jiao Shoutao, Zhou Yongzhang, Zhang Qi, et al. Study on Intelligent Discrimination of Tectonic Settings Based on Global Gabbro Data from GEOROC[J]. Acta Petrologica Sinica, 2018, 34(11): 3189-3194. [3] Ueki K, Hino H, Kuwatani T. Geochemical Discrimination and Characteristics of Magmatic Tectonic Settings: A Machine-Learning-Based Approach[J]. Geochemistry, Geophysics, Geosystems, 2017, 19(4): 1327-1347. [4] 韩启迪,张小桐,申维. 基于决策树特征提取的支持向量机在岩性分类中的应用[J]. 吉林大学学报(地球科学版),2019,49(2): 611-620. Han Qidi, Zhang Xiaotong, Shen Wei. Application of Support Vector Machine Based on Decision Tree Feature Extraction in Lithology Classification[J]. Journal of Jilin University (Earth Science Edition), 2019, 49(2): 611-620. [5] 王思琪,王明常,王凤艳,等. 基于SAE-ELM方法的多金属遥感地球化学反演[J]. 世界地质,2020,39(4): 195-202. Wang Siqi, Wang Mingchang, Wang Fengyan, et al. Remote Sensing Geochemical Inversion of Multi Metal Materials Based on SAE-ELM[J]. Global Geology, 2020, 39(4): 195-202. [6] 徐述腾,周永章. 基于深度学习的镜下矿石矿物的智能识别实验研究[J]. 岩石学报,2018,34(11): 3244-3252. Xu Shuteng, Zhou Yongzhang. Artificial Intelligence Identification of Ore Minerals Under Microscope Based on Deep Learning Algorithm[J]. Acta Petrologica Sinica, 2018, 34(11): 3244-3252. [7] 刘力辉,陆蓉,杨文魁. 基于深度学习的地震岩相反演方法[J]. 石油物探,2019,58(1): 123-129. Liu Lihui, Lu Rong, Yang Wenkui. Seismic Lithofacies Inversion Based on Deep Learning[J]. Geophysical Prospecting for Petroleum, 2019, 58(1): 123-129. [8] 闫佰忠,孙剑,王昕洲,等. 基于多变量LSTM神经网络的地下水水位预测[J]. 吉林大学学报(地球科学版),2020,50(1): 208-216. Yan Baizhong, Sun Jian, Wang Xinzhou, et al. Multivariable LSTM Neural Network Model for Groundwater Levels Prediction[J]. Journal of Jilin University (Earth Science Edition), 2020, 50(1): 208-216. [9] 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. Liu Yanpeng, Zhu Lixin, Zhou Yongzhang. Application of Convolutional Neural Network in Prospecting Prediction of Ore Deposits: Taking the Zhaojikou Pb-Zn Ore Deposit in Anhui Province as a Case[J]. Acta Petrologica Sinica, 2018, 34(11): 3217-3224. [10] Zuo R, Xiong Y. Big Data Analytics of Identifying Geochemical Anomalies Supported by Machine Learning Methods[J]. Natural Resources Research, 2018, 27(1): 5-13. [11] Ghezelbash R, Maghsoudi A, Carranza E J M. Performance Evaluation of RBF- and SVM-Based Machine Learning Algorithms for Predictive Mineral Prospectivity Modeling: Integration of S-A Multifractal Model and Mineralization Controls[J]. Earth Science Informatics, 2019, 12: 277-293. [12] Mercadier J, Cuney M, Lach P, et al. Origin of Uranium Deposits Revealed by Their Rare Earth Element Signature[J]. Terra Nova, 2011, 23(4): 264-269. [13] Frimmel H E, Schedel S, Brätz H. Uraninite Chemistry as Forensic Tool for Provenance Analysis[J]. Applied Geochemistry, 2014, 48: 104-121. [14] Eglinger A, André-Mayer A S, Vanderhaeghe O, et al. Geochemical Signatures of Uranium Oxides in the Lufilian Belt: From Unconformity-Related to Syn-Metamorphic Uranium Deposits During the Pan-African Orogenic Cycle[J]. Ore Geology Reviews, 2013, 54: 197-213. [15] Gandhi S S, Potter E G, Fayek M. New Constraints on Genesis of the Polymetallic Veins at Port Radium, Great Bear Lake, Northwest Canadian Shield[J]. Ore Geology Reviews, 2018, 96: 28-47. [16] Petrelli M, Perugini D. Solving Petrological Problems Through Machine Learning: The Study Case of Tectonic Discrimination Using Geochemical and Isotopic Data[J]. Contributions to Mineralogy and Petrology, 2016, 171(10): 81. [17] Ren Q B, Li M C, Han S. Tectonic Discrimination of Olivine in Basalt Using Data Mining Techniques Based on Major Elements: A Comparative Study from Multiple Perspectives[J]. Big Earth Data, 2019, 3(1): 8-25. [18] Balboni E, Jones N, Spano T, et al. Chemical and Sr Isotopic Characterization of North America Uranium Ores: Nuclear Forensic Applications[J]. Applied Geochemistry, 2016, 74: 24-32. [19] Abdi H, Williams L J. Principal Component Analysis[J]. Wiley Interdisciplinary Reviews Computational Statistics, 2010, 2(4): 433-459. [20] Cortes C, Vapnik V. Support-Vector Networks[J]. Machine Learning, 1995, 20(3): 273-297. [21] Hsu C W, Lin C J. A Comparison of Methods for Multiclass Support Vector Machines[J]. IEEE Transactions on Neural Networks, 2002, 13(2): 415-425. [22] 李苍柏,肖克严,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. Li Cangbai, Xiao Keyan, Li Nan, et al. A Comparative Study of Support Vector Machine, Random Forest and Artificial Neural Network Machine Learning Algorithms in Geochemical Anomaly Information Extraction[J]. Acta Geoscientica Sinica, 2020, 41(2): 309-319. [23] 刘祥楼, 贾东旭, 李辉, 等. 说话人识别中支持向量机核函数参数优化研究[J]. 科学技术与工程,2010, 10(7): 1669-1673. Liu Xianglou, Jia Dongxu, Li Hui, et al. Research on Kernel Parameter Optimization of Support Vector Machine in Speaker Recognition[J]. Science Technology and Engineering, 2010, 10(7): 1669-1673. [24] Arlot S, Celisse A. A Survey of Cross-Validation Procedures for Model Selection[J]. Statistics Surveys, 2010, 4: 40-79. [25] 宋永东. 支持向量机参数选择的研究[D]. 武汉:华中师范大学,2013. Song Yongdong. Research of Parameter Selection for Support Vector Machine[D]. Wuhan: Central China Normal University, 2013. [26] Rodriguez J D, Perez A, Lozano J A. Sensitivity Analysis of K-Fold Cross Validation in Prediction Error Estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(3): 569-575. [27] 骆金诚. 粤北花岗岩型铀矿床成因机制研究:矿物学和铀矿物U-Pb年代学及地球化学约束[D]. 北京:中国科学院大学,2015. Luo Jincheng. Genesis of Granite-Hosted Uranium Deposits in the Northern Guangdong, China: Constraints from Mineralogy, Uranium Mineral U-Pb Geochronology and Geochemistry[D]. Beijing: University of Chinese Academy of Sciences, 2015. [28] McLennan S, Taylor S. Rare Earth Element Mobility Associated with Uranium Mineralization[J]. Nature, 1979, 282: 247-250. [29] Alexandre P, Kyser T K. Effects of Cationic Substitutions and Alteration in Uraninite, and Implications for the Dating of Uranium Deposits[J]. Canadian Mineralogist, 2005, 43(3): 1005-1017. [30] Anders E, Grevesse N. Abundances of the Elements: Meteoritic and Solar[J]. Geochimica et Cosmochimica Acta, 1989, 53(1): 197-214. [31] 任秋兵,李明超,韩帅. 基于改进遗传算法-神经网络的玄武岩构造环境判别及对比实验[J].地学前缘,2019,26(4): 117-124. Ren Qiubing, Li Mingchao, Han Shuai. Discrimination and Comparison Experiments of Basalt Tectonic Setting Based on Improved Genetic Algorithm-Optimized Neural Network[J]. Earth Science Frontiers, 2019, 26(4): 117-124. [32] 刘承照,韩帅,李明超,等. 耦合PCA-SVM算法的金矿矿床规模预测分析研究[J]. 地学前缘,2019,26(4): 138-145. Liu Chengzhao, Han Shuai, Li Mingchao,et al. Prediction and Analysis of Gold Deposit Sizes Based on Coupled PCA-SVM Algorithm[J]. Earth Science Frontiers, 2019, 26(4): 138-145. [33] 张野,李明超,韩帅,等. 基于金矿规格单元数据的机器学习方法在成矿建模分析中的应用[J]. 大地构造与成矿学,2020,44(2): 183-191. Zhang Ye, Li Mingchao, Han Shuai,et al. Machine Learning Methods Application in Gold Mineralization Prediction Based on Gold Unit Data[J]. Geotectonica et Metallogenia, 2020, 44(2): 183-191. [34] 任秋兵,李明超,李玉琼,等. 基于全球橄榄石数据的玄武岩构造环境智能判别方法及其验证[J]. 大地构造与成矿学,2020,44(2): 212-221. Ren Qiubing, Li Mingchao, Li Yuqiong, et al. An Intelligent Method for Geochemical Discrimination of Tectonic Settings of Basalt Based on Olivine Composition: GWO-SVM Method and Its Verification[J]. Geotectonica et Metallogenia, 2020, 44(2): 212-221. |
[1] | 熊越晗, 刘东燕, 刘东升, 王艳磊, 唐小山. 基于岩样细观图像深度学习的岩性自动分类方法[J]. 吉林大学学报(地球科学版), 2021, 51(5): 1597-1604. |
[2] | 王博帅, 蒲东川, 李婷婷, 牛雪峰. 基于多源遥感影像的长春市城市建成区提取[J]. 吉林大学学报(地球科学版), 2021, 51(4): 1284-1294. |
[3] | 牟丹, 张丽春, 徐长玲. 3种经典机器学习算法在火山岩测井岩性识别中的对比[J]. 吉林大学学报(地球科学版), 2021, 51(3): 951-956. |
[4] | 魏博, 赵建斌, 魏彦巍, 李振林, 熊葵. 福山凹陷白莲流二段储层分类方法[J]. 吉林大学学报(地球科学版), 2020, 50(6): 1639-1647. |
[5] | 郝宇杰, 商青青, 任云生, 刘小禾, 陈聪. LA-ICP-MS原位分析白钨矿稀土元素[J]. 吉林大学学报(地球科学版), 2020, 50(4): 1029-1041. |
[6] | 张辉, 刘万军, 吕欢欢. 引导滤波联合局部判别嵌入的高光谱影像分类[J]. 吉林大学学报(地球科学版), 2020, 50(4): 1249-1260. |
[7] | 方石, 赵云. 比较沉积学概念体系的厘定与重构[J]. 吉林大学学报(地球科学版), 2020, 50(2): 480-499. |
[8] | 李向东, 何幼斌. 宁夏香山群徐家圈组顶部石灰岩稀土元素特征与沉积介质分析[J]. 吉林大学学报(地球科学版), 2020, 50(1): 139-157. |
[9] | 白韬, 杨国东, 王凤艳, 刘佳为. 一种面向对象的最优分割尺度计算模型[J]. 吉林大学学报(地球科学版), 2020, 50(1): 304-312. |
[10] | 董晋琨, 杨眉, 吴志远, 秦善, 王雨薇. 系统矿物学数据特征分析及数据库建设[J]. 吉林大学学报(地球科学版), 2019, 49(3): 727-736. |
[11] | 尹超, 周爱红, 袁颖, 王帅伟. 基于邻域粗糙集和支持向量机的固结系数预测[J]. 吉林大学学报(地球科学版), 2019, 49(3): 746-754. |
[12] | 叶涛, 韦阿娟, 黄志, 赵志平, 肖述光. 基于主成分分析法与Bayes判别法组合应用的火山岩岩性定量识别:以渤海海域中生界为例[J]. 吉林大学学报(地球科学版), 2019, 49(3): 872-879. |
[13] | 贺金鑫, 姜天, 董永胜, 韩凯旭, 马宁, 熊玥. 基于Landsat 8的辽宁弓长岭区遥感蚀变信息提取[J]. 吉林大学学报(地球科学版), 2019, 49(3): 893-901. |
[14] | 韩启迪, 张小桐, 申维. 基于决策树特征提取的支持向量机在岩性分类中的应用[J]. 吉林大学学报(地球科学版), 2019, 49(2): 611-620. |
[15] | 李林翠, 李喜安, 洪勃, 王力. 不同埋深马兰黄土孔隙结构试验[J]. 吉林大学学报(地球科学版), 2019, 49(2): 493-503. |
|