耦合PCA-SVM算法的金矿矿床规模预测分析研究
|
摘要
判断矿床(点)的类型是矿床勘探中的重要内容,传统预测金矿成矿规模的方法不仅耗时耗力,而且所需的经济成本较大。为提高矿床规模的勘探效率和准确度,揭示元素与金矿成矿规模的潜在联系,文中提出了耦合主成分分析(principal component analysis,PCA)和支持向量机(support vector machine,SVM)算法的预测分析PCA-SVM(principal component analysis-support vector machine)方法。该方法先通过主成分分析提取数据中的主要特征,再将主要特征带入支持向量机算法,从而训练出最优分类器以预测金矿成矿规模。文中共使用了3 812个金矿样本数据用于学习训练和预测分析,训练准确率为92.3%,测试准确率为88.7%,分别比直接使用支持向量机算法高出14.3%和17.1%。基于PCA-SVM的预测模型,不仅消除了人为主观因素的影响,而且有效提高了勘探过程中矿床预测的准确率和矿床勘探的效率,为地质勘查工作提供依据。
Identification of ore deposit types is an important part of mineral exploration.Traditional methods for predicting deposit size are time-consuming,laborious and costly.In order to improve prospecting efficiency and accuracy and reveal potential relation between chemical composition and the size of gold mineralization,we propose here an integrated approach using the Principal Component Analysis(PCA)and Support Vector Machine(SVM)algorithms.In this approach,we first extract the major features of samples using PCA,and we then train a set of SVM classifiers by these features to predict deposit sizes.In this study,we collected and analyzed 3812 gold mine samples from Beishan,Gansu region to establish a PCA-SVM model with the training accuracy of 92.3% and the test accuracy of 88.7%,which were 14.3% and 17.1%higher,respectively,than using SVM.We demonstrated that the PCA-SVM method not only can eliminate subjective factors,but also can improve the accuracy of identifying ore deposits as well as prospecting efficiency,thus to provide reliable support for decision making.
Identification of ore deposit types is an important part of mineral exploration.Traditional methods for predicting deposit size are time-consuming,laborious and costly.In order to improve prospecting efficiency and accuracy and reveal potential relation between chemical composition and the size of gold mineralization,we propose here an integrated approach using the Principal Component Analysis(PCA)and Support Vector Machine(SVM)algorithms.In this approach,we first extract the major features of samples using PCA,and we then train a set of SVM classifiers by these features to predict deposit sizes.In this study,we collected and analyzed 3812 gold mine samples from Beishan,Gansu region to establish a PCA-SVM model with the training accuracy of 92.3% and the test accuracy of 88.7%,which were 14.3% and 17.1%higher,respectively,than using SVM.We demonstrated that the PCA-SVM method not only can eliminate subjective factors,but also can improve the accuracy of identifying ore deposits as well as prospecting efficiency,thus to provide reliable support for decision making.
引文
[1]万虎,李晓晓.浅谈普查找矿与矿床勘探方法[J].西部资源,2017(3):40-41.
[2]彭涛.探究地质工程测量技术的常见问题与对策[J].科技经济导刊,2017(27):89,43.
[3]薛建平,李成元,刘永新,等.试论造山带1∶5万地质填图法的应用效果:以索伦山地区的区矿调工作为例[J].内蒙古煤炭经济,2014(11):209-212.
[4]胡思颐.当代金刚石找矿工作中的重砂法[J].地质科技情报,1991(增刊1):125-134.
[5]杨少平,弓秋丽,文志刚,等.地球化学勘查新技术应用研究[J].地质学报,2011,85(11):1844-1877.
[6]杨少平,孔牧,刘华忠,等.我国东北部森林沼泽景观区化探扫面方法技术研究[J].地质与勘探,2003,39(6):94-98.
[7]方维萱,郭玉乾.基于风险分析的商业性找矿预测新方法与应用[J].地学前缘,2009,16(2):209-226.
[8]蔡婷婷.环境地球化学勘查成果的表示与评价[J].黑龙江科技信息,2012(35):18.
[9]谢学锦,任天祥,严光生,等.进入21世纪中国化探发展路线图[J].中国地质,2010,37(2):245-267.
[10]李文昌,刘学龙.云南普朗斑岩型铜矿田构造岩相成矿规律与控矿特征[J].地学前缘,2015,22(4):53-66.
[11]汤中立.中国镁铁、超镁铁岩浆矿床成矿系列的聚集与演化[J].地学前缘,2004,11(1):113-119.
[12]罗建民,王晓伟,宋秉田,等.岩浆岩定量分类方法探讨:以甘肃省西秦岭地区为例[J].岩石学报,2018,34(2):326-332.
[13]罗建民,张琪,宋秉田,等.物化探信息综合处理在找矿靶区定量优选中的应用[J].矿物岩石地球化学通报,2017,36(6):886-890.
[14]陈建平,陈勇,王全明.基于GIS的多元信息成矿预测研究:以赤峰地区为例[J].地学前缘,2008,15(4):18-26.
[15] ZAINI N,FREEK V D M,HARALD V D W.Determination of carbonate rock chemistry using laboratory-based hyperspectral imagery[J].Remote Sensing,2014,6(5):4149-4172.
[16] SADEGHI B,MADANI N,CARRANZA E J M.Combination of geostatistical simulation and fractal modeling for mineral resource classification[J].Journal of Geochemical Exploration,2015,149:59-73.
[17] NOVAES C G,ROMOIL D S,SANTOS B G,et al.Screening of Passiflora L.mineral content using principal component analysis and Kohonen self-organizing maps[J].Food Chemistry,2017,233:507-513.
[18] LUO X,XU Y, WANG W,et al.Towards enhancing stacked extreme learning machine with sparse autoencoder by correntropy[J].Journal of the Franklin Institute,2018,355(4):1945-1966.
[19]朱志洁,张宏伟,韩军,等.基于PCA-BP神经网络的煤与瓦斯突出预测研究[J].中国安全科学学报,2013,23(4):45-50.
[20]牟丹,王祝文,黄玉龙,等.基于SVM测井数据的火山岩岩性识别:以辽河盆地东部坳陷为例[J].地球物理学报,2015,58(5):1785-1793.
[21] LI M,LU M,SHI J.Analyzing heating equipment's operations based on measured data[J].Energy and Buildings,2014,82:47-56.
[22]李昆仑,黄厚宽,田盛丰.一种基于有向无环图的多类SVM分类器[J].模式识别与人工智能,2003,16(2):164-168.
[2]彭涛.探究地质工程测量技术的常见问题与对策[J].科技经济导刊,2017(27):89,43.
[3]薛建平,李成元,刘永新,等.试论造山带1∶5万地质填图法的应用效果:以索伦山地区的区矿调工作为例[J].内蒙古煤炭经济,2014(11):209-212.
[4]胡思颐.当代金刚石找矿工作中的重砂法[J].地质科技情报,1991(增刊1):125-134.
[5]杨少平,弓秋丽,文志刚,等.地球化学勘查新技术应用研究[J].地质学报,2011,85(11):1844-1877.
[6]杨少平,孔牧,刘华忠,等.我国东北部森林沼泽景观区化探扫面方法技术研究[J].地质与勘探,2003,39(6):94-98.
[7]方维萱,郭玉乾.基于风险分析的商业性找矿预测新方法与应用[J].地学前缘,2009,16(2):209-226.
[8]蔡婷婷.环境地球化学勘查成果的表示与评价[J].黑龙江科技信息,2012(35):18.
[9]谢学锦,任天祥,严光生,等.进入21世纪中国化探发展路线图[J].中国地质,2010,37(2):245-267.
[10]李文昌,刘学龙.云南普朗斑岩型铜矿田构造岩相成矿规律与控矿特征[J].地学前缘,2015,22(4):53-66.
[11]汤中立.中国镁铁、超镁铁岩浆矿床成矿系列的聚集与演化[J].地学前缘,2004,11(1):113-119.
[12]罗建民,王晓伟,宋秉田,等.岩浆岩定量分类方法探讨:以甘肃省西秦岭地区为例[J].岩石学报,2018,34(2):326-332.
[13]罗建民,张琪,宋秉田,等.物化探信息综合处理在找矿靶区定量优选中的应用[J].矿物岩石地球化学通报,2017,36(6):886-890.
[14]陈建平,陈勇,王全明.基于GIS的多元信息成矿预测研究:以赤峰地区为例[J].地学前缘,2008,15(4):18-26.
[15] ZAINI N,FREEK V D M,HARALD V D W.Determination of carbonate rock chemistry using laboratory-based hyperspectral imagery[J].Remote Sensing,2014,6(5):4149-4172.
[16] SADEGHI B,MADANI N,CARRANZA E J M.Combination of geostatistical simulation and fractal modeling for mineral resource classification[J].Journal of Geochemical Exploration,2015,149:59-73.
[17] NOVAES C G,ROMOIL D S,SANTOS B G,et al.Screening of Passiflora L.mineral content using principal component analysis and Kohonen self-organizing maps[J].Food Chemistry,2017,233:507-513.
[18] LUO X,XU Y, WANG W,et al.Towards enhancing stacked extreme learning machine with sparse autoencoder by correntropy[J].Journal of the Franklin Institute,2018,355(4):1945-1966.
[19]朱志洁,张宏伟,韩军,等.基于PCA-BP神经网络的煤与瓦斯突出预测研究[J].中国安全科学学报,2013,23(4):45-50.
[20]牟丹,王祝文,黄玉龙,等.基于SVM测井数据的火山岩岩性识别:以辽河盆地东部坳陷为例[J].地球物理学报,2015,58(5):1785-1793.
[21] LI M,LU M,SHI J.Analyzing heating equipment's operations based on measured data[J].Energy and Buildings,2014,82:47-56.
[22]李昆仑,黄厚宽,田盛丰.一种基于有向无环图的多类SVM分类器[J].模式识别与人工智能,2003,16(2):164-168.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |