利用区域化探数据推断地质体空间分布

详细信息    查看全文 | 推荐本文 |

英文篇名：Inferring Spatial Distribution of Geological Bodies by Virtue of Regional Geochemical Survey Data 作者：徐剑波 ; 陈军林 英文作者：XU Jianbo;CHEN Junlin;The First Geological Institute of the China Metallurgical Geology Bureau;School of Earth Sciences and Resources,China University of Geosciences(Beijing); 关键词：化探 ; 数据挖掘 ; 随机森林 ; 分类 ; 非平衡数据 英文关键词：geochemical exploration;;data mining;;random forest;;classification;;unbalanced data set 中文刊名：地质与勘探 英文刊名：Geology and Exploration 机构：中国冶金地质总局第一地质勘查院;中国地质大学(北京)地球科学与资源学院; 出版日期：2019-09-15 出版单位：地质与勘探 年：2019 期：05 语种：中文; 页：100-108 页数：9 CN：11-2043/P ISSN：0495-5331 分类号：P632

摘要

区域化探数据可以反映地层的空间分布,利用区域化探数据借助有效的数据挖掘方法,能够提取出其中包含的地质信息,对于覆盖区填图以及矿产勘查有重要意义,其中的关键问题是如何进行数据挖掘。随机森林算法是近年来热门的机器学习方法,本文应用随机森林算法结合非平衡数据集分类方法提出了一种新的化探数据挖掘方法,通过实例研究验证表明该方法准确率高,能够有效地提取出区域化探数据中的地质信息。
        Regional geochemical survey data can be used to infer the spatial distribution of geological bodies in the subsurface. It is of great significance for mapping covered areas and mineral exploration. To do so,the key problem is how to conduct data mining and extract useful information. The algorithm random forest is a popular machine learning method in recent years. In this paper,we put forward a new method of mining geochemical data by using the random forest algorithm coupled with unbalanced dataset classification. A case study shows that this method has high accuracy and can extract geological information from regional geochemical data effectively.

引文

Al-Stouhi S,Reddy C K.2016.Transfer learning for class imbalance problems with inadequate data[J].Knowledge&Information Systems,48(1):201-228．
    Barnett C T,Williams P M.2009.Using geochemistry and neural networks to map geology under glacial cover[J].Geoscience BC,3(1):26．
    Batista G E A P A,Prati R C,Monard MC.2004.A study of the behavior of several methods for balancing machine learning training data[J].Acm Sigkdd Explorations Newsletter,6(1):20-29．
    Breiman L.2001.Random forests[J].Machine Learning,45(1):5-32．
    Chawla N V,Bowyer K W,Hall L O,Philip Kegelmeyer W.2002.SMOTE:Synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,16(1):321-357．
    Chen Junlin,Peng Runmin,Li Shuaizhi,Chen Xicai.2017.Self-organizing feature map neural network and K-means algorithm as a data excavation tool for obtaining geological information from regional geochemical exploration data[J].Geophysical and Geochemical Exploration,41(5):919-927(in Chinese with English abstract)．
    Gao Hongsheng,Zhang Quan,Cao Shuping,Xu Fang,Zhang Yana,Cheng Xujiang.2014.The application of the ternary diagram to geological body division and anomaly evaluation in regional ceochemical exploration[J].Geophysical and Geochemical Exploration,38(2):377-384(in Chinese with English abstract)．
    Ghanbari Y,Hezarkhani A,Ataei M,Pazand K.2010.Regional geochemical pattern recognition with multivariate correspondence cluster analysis in the Ravar area,Iran[J].Applied Earth Science,119(4):220-226．
    Gordey S P.2008.Geology,Selwyn Basin(105J and 105K),Yukon[J].Geological Survey of Canada,Open File:5438．
    Green P M.1984.Digital image-processing of integrated geochemical and geological information[J].Journal of the Geological Society,141(9):941-949．
    Hao Libo,Lu Jilong,Li Long,Mo Gensheng,Yan Guangsheng,Shi Yanxiang,Zhao Yuyan.2007.Method of using regional geochemical data in geological mapping in shallow overburden areas[J].Geology in China,34(4):710-715(in Chinese with English abstract)．
    Hao Libo,Lu Jilong,Ma Li.2005.Relation between the chemical composition residual soils and bedrocks in shallow overburden areas and its significance-A case study of the northern Da Xingan Mountains[J].Geology in China,32(3):477-482(in Chinese with English abstract)．
    He H,Garcia E A.2009.Learning from imbalanced data[J].IEEE Transactions on Knowledge&Data Engineering,21(9):1263-1284．
    Liao Guozhong,Zhang Wei,Liang Shengxian,Wu Wenxian.2018.A geochemical anomaly analysis method based on river basins:An example of the Yata area[J].Geology and Exploration,54(2):315-324(in Chinese with English abstract)．
    Liu Xueyi,Li Ping,Gao Chuanhou.2001.Fast leave-one-out crossvalidation algorithm for extreme learning machine[J].Journal of Shanghai Jiao Tong University,45(8):1140-1145(in Chinese with English abstract)．
    Ma Xiaoyang,Bai Xianqing,Zang Xiaofan,Geng Weihua.2005.New regional geochemical exploration method in basic geological survey of Shalanzhan sheet forest-swamp area,Heilongjiang Province[J].Geophysical and Geochemical Exploration,29(2):108-110(in Chinese with English abstract)．
    Prati R C,Batista G E A P A,Monard MC.2008.A study with class imbalance and random sampling for a decision tree learning system[J].Artificial Intelligence in Theory and Practice II.Springer US,276:131-140．
    Rantitsch G.2000.Application of fuzzy clusters to quantify lithological background concentrations in stream-sediment geochemistry[J].Journal of Geochemical Exploration,71(1):73-82．
    Shi Changyi,Ren Yuansheng.2005.Fundamental geological problems in regional geochemical exploration data[J].Geology and Exploration,41(3):53-58(in Chinese with English abstract)．
    Shi Yanxiang,Hao Libo,Lu Jilong,Ji Hongjin.2008.Application of factor classification in geological mapping in Tahe area,Heilongjiang Province[J].Journal of Jilin Unviersity:Earth Science Edition,38(5):899-903(in Chinese with English abstract)．
    Shiva M,Aryafar A,Zaremotlagh S.2011.Fuzzy c-means cluster analysis,a robust multivariate technique in stream sediment geochemical exploration,a case study in eastern part of Iran,Birjand[J].Journal of Geology and Mining Research,3(1):1-6．
    Steenfelt A.1987.Geochemical mapping and prospecting in GreenlandA review of results and experience[J].Journal of Geochemical Exploration,29(87):183-205．
    Steenfelt A.1990.Geochemical patterns related to major tectono-stratigraphic units in the Precambrian of northern Scandinavia and Greenland[J].Journal of Geochemical Exploration,39(s1-2):35-48．
    Vriend S P,van Gaans P F M,Middelburg J,Ton de Nijs.1988.The application of fuzzy c-means cluster analysis and non-linear mapping to geochemical datasets:Examples from Portugal[J].Applied Geochemistry,3(2):213-224．
    Xiang Yunchuan,Gong Qingjie,Liu Rongmei,Yang Wanzhi.2014.Model and application of deducing geological body on regional geochemical survey data:A case study on granitic intrusions in China[J].Acta Petrologica Sinica,30(9):2609-2618(in Chinese with English abstract)．
    Xu Guozhi,Xu Jinpeng,Duan Lingling.2015.The application of geochemical data in geological mapping[J].Geophysical and Geochemical Exploration,39(3):450-455(in Chinese with English abstract)．
    Zhang Wenping.1993.Statistical processing method of data below detection limit in environmental monitoring[J].Shanghai Environmental Science,11(11):38-40(in Chinese)．
    Zhao Juan,Wang Taishan,Li Debiao,Ma Zhengting,Wei Liqiong.2017.The techniques and application achievements in 1∶50000 stream sediment survey of the Qimantage area,Qinghai Province[J].Geology and Exploration,53(4):739-745(in Chinese with English abstract)．
    Zhi Weimei,Guo Huaping,Fan Ming,Ye Yangdong.2012.Discussion of classification for imbalance data set[J].Computer Science,39(B06):304-308(in Chinese with English abstract)．
    陈军林，彭润民，李帅值，陈喜财．2017．利用自组织特征映射神经网络和K-means聚类算法挖掘区域化探数据中的地质信息[J]．物探与化探，41(5):919-927．
    高洪生，张全，曹淑萍，徐方，张亚娜，程旭江．2014．区域化探中利用三元图进行地质体划分及异常评价[J]．物探与化探，38(2):377-384．
    郝立波，陆继龙，李龙，莫根生，严光生，时艳香，赵玉岩．2007．区域化探数据在浅覆盖区地质填图中的应用方法研究[J]．中国地质，34(4):710-715．
    郝立波，陆继龙，马力．2005．浅覆盖区土壤化学成分与基岩化学成分的关系及其意义-以大兴安岭北部地区为例[J]．中国地质，32(3):477-482．
    廖国忠，张伟，梁生贤，吴文贤．2018．基于水系流域的地球化学异常分析方法-以1∶50000丫他幅水系沉积物分析为例[J]．地质与勘探，54(2):315-324．
    刘学艺，李平，郜传厚．2011．极限学习机的快速留一交叉验证算法[J]．上海交通大学学报，45(8):1140-1145．
    马晓阳，白显清，臧晓凡，耿卫华．2005．黑龙江沙兰站幅森林沼泽区基础地质调查中的区域化探新方法[J]．物探与化探，29(2):108-110．
    时艳香，郝立波，陆继龙，纪宏金．2008．因子分类法在黑龙江塔河地区地质填图中的应用[J]．吉林大学学报:地球科学版，38(5):899-903．
    史长义，任院生．2005．区域化探资料研究基础地质问题[J]．地质与勘探，41(3):53-58．
    向运川，龚庆杰，刘荣梅，杨万志．2014．区域地球化学推断地质体模型与应用-以花岗岩类侵入体为例[J]．岩石学报，30(9):2609-2618．
    徐国志，徐锦鹏，段玲玲．2015．化探资料在地质填图中的应用[J]．物探与化探，39(3):450-455．
    张文平．1993．环境监测中低于检出限数据的统计处理方法[J]．上海环境科学，11(11):38-40．
    赵娟，王泰山，李德彪，马正婷，魏立琼．2017．青海祁漫塔格地区1∶5万水系沉积物测量方法技术及应用成果[J]．地质与勘探，53(4):739-745．
    职为梅，郭华平，范明，叶阳东．2012．非平衡数据集分类方法探讨[J]．计算机科学，39(B06):304-308.