地球化学异常识别的两种机器学习算法之比较
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Comparison of two machine learning algorithms for geochemical anomaly detection
  • 作者:郑泽宇 ; 赵庆英 ; 李湜先 ; 邱士龙
  • 英文作者:ZHENG Ze-yu;ZHAO Qing-ying;LI Shi-xian;QIU Shi-long;College of Earth Sciences,Jilin University;
  • 关键词:一类支持向量机 ; 孤独森林 ; 地球化学异常 ; ROC曲线
  • 英文关键词:one-class support vector machine;;isolation forest;;geochemical anomaly;;ROC curve
  • 中文刊名:SJDZ
  • 英文刊名:Global Geology
  • 机构:吉林大学地球科学学院;
  • 出版日期:2018-12-25
  • 出版单位:世界地质
  • 年:2018
  • 期:v.37
  • 基金:国家自然科学基金面上项目(41472299、41672322);; 中国地质调查局资助项目(1212010510218)联合资助
  • 语种:中文;
  • 页:SJDZ201804031
  • 页数:7
  • CN:04
  • ISSN:22-1111/P
  • 分类号:300-306
摘要
在Sklearn的Python语言代码基础上,开发了基于孤独森林和一类支持向量机的多元地球化学异常识别方法程序。选择吉林省和龙地区为实验区,从1∶5万水系沉积物资料中提取地球化学异常。把实验区已知矿点的空间分布位置作为"地真"数据,绘制两种机器学习算法的ROC曲线并计算AUC值,用来对比两种方法的多元地球化学异常识别效果。研究结果表明:两种机器学习算法都能够有效识别多元地球化学异常,所提取的多元地球化学异常与已知矿点具有显著的空间关联性;孤独森林算法在数据处理耗时和多元地球化学异常识别效果方面略优于一类支持向量机。
        The programs for multivariate geochemical anomaly detection with isolation forest and one-class support vector machine were developed based on the Python source codes of Sklearn. The geochemical anomalies were extracted from the stream sediment survey data of 1∶ 50 000 scale collected from the Helong area,Jilin Province. By using the spatial locations of known mineral occurrences in the study area as the ground truth data,the ROC curves of the two algorithms were plotted and the AUC values were computed for comparing the performance of the two algorithms in geochemical anomaly detection. The results show that the two algorithms can properly identify geochemical anomalies,and the extracted geochemical anomalies are significantly spatially associated with the known mineral occurrences. Isolation forest slightly outperforms one-class support vector machine in terms of data modeling efficiency and geochemical anomaly detection performance.
引文
[1] Chen Y L,Lu L J,Li X B. Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly[J]. Journal of Geochemical Exploration,2014,140:56-63.
    [2] Sch9lkopf B,Platt J,Shawe-Taylor J,et al. Estimating the support of a high-dimensional distribution[J]. Neural Computation,2001,13:1443-1471.
    [3] Chen Y L,Wu W. Mapping mineral prospectivity by using one-class support vector machine to identify multivariate geological anomalies from digital geological survey data[J]. Australian Journal of Earth Sciences,2017,44(5):639-651.
    [4] Chen Y L,Wu W. Application of one-class support vector machine to quickly identify multivariate anomalies from geochemical exploration data[J]. Geochemistry Exploration Environment Analysis,2017,17:231-238.
    [5] Liu F T,Ting K M,Zhou Z H. Isolation forest[C].Proceedings of the Eighth IEEE International Conference on Data Mining(ICDM),2008:413-422.
    [6] Wu W,Chen Y L. Application of isolation forest to extract multivariate anomalies from geochemical exploration data[J]. Global Geology,2018,21(1):36-47.
    [7] Chen Y L,Wu W. Isolation forest as an alternative datadriven mineral prospectivity mapping method with a higher data-processing efficiency[J]. Natural Resources Research, 2018, https://doi. org/10. 1007/s11053-018-9375-6.
    [8] Zhang Y B,Wu F Y,Wilde S A,et al. Zircon U-Pb ages and tectonic implications of Early Paleozoic granitoids at Yanbian,Jilin Province,Northeast China[J]. Island Arc,2004,13(4):484-505.
    [9] Wu F,Lin J,Wilde S A,et al. Nature and significance of Early Cretaceous giant igneous event in eastern China[J]. Earth and Planetary Science Letters,2005,233:103-119.
    [10] Yu J J,Wang F,Xu W L,et al. Early Jurassic mafic magmatism in the Lesser Xing'an-Zhangguangcai Range,NE China, and its tectonic implications:constraints from zircon U-Pb chronology and geochemistry[J].Lithos,2012:142-143,256-266.
    [11]武鹏飞,孙德有,王天豪,等.延边和龙地区闪长岩的年代学、地球化学特征及岩石成因研究[J].高校地质学报,2013,19(4):600-610.WU Peng-fei,SUN De-you,WANG Tian-hao,et al.Chronology,geochemical characteristic and petrogenesis analysis of diorite in Helong of Yanbian area,northeastern China[J]. Geological Journal of China Universities,2013,19(4):600-610.
    [12]闫冬,李楠,徐曼,等.吉林省和龙市百里坪银矿床成矿特征及成因探讨[J].吉林地质,2015,34(3):36-41.YAN Dong,LI Nan,XU Man,et al. Mineralization characteristics and genesis of the Bailiping silver deposit in Helong City, Jilin Province[J]. Jilin Geology,2015,34(3):36-41.
    [13]万文周,王家斌,冯修云,等.吉林省和龙市和安河金矿床地质特征及找矿方向[J].吉林地质,2010,29(1):71-75.WAN Wen-zhou,WANG Jia-bin,FENG Xiu-yun,et al. Geological features and prospecting directions of the He'anhe gold deposit in the Helong area,Jilin Province,China[J]. Jilin Geology,2010,29(1):71-75.
    [14]潘月栋,许宝剑,孙洋,等.吉林省和龙市金城洞金矿地质特征[J].吉林地质,2016,35(1):30-35.PAN Yue-dong,XU Bao-jian,SUN Yang,et al. Geological features of the Jinchengdong gold deposit in Helong City,Jilin Province,China[J]. Jilin Geology,2016,35(1):30-35.
    [15]刘凤山,张茂林.做好新一轮国土资源大调查质量管理工作[J].中国地质,1999,26(8):20-21.LIU Feng-shan, ZHANG Mao-lin. Complete quality management of the new-round land resources survey[J]. Chinese Geology,1999,26(8):20-21.
    [16] Zhang J,Marszalek M,Lazebnik S,et al. Local features and kernels for classification of texture and object categories:a comprehensive study[J]. International Journal of Computer Vision,2007,73(2):213-238.
    [17] Susto G A,Beghi A,McLoone S. Anomaly detection through on-line isolation forest:an application to plasma etching[C]//28th Annual SEMI Advanced Semiconductor Manufacturing Conference(ASMC 2017),Saratoga Springs,USA,2017:89-94.

© 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