模式识别-人工神经网络方法评价化探异常  

PATTERN RECOGNITION AND ARTIFICIAL NEURAL NETWORK APPLIED TO EVALUATION OF GEOCHEMICAL ANOMALIES IN THE SOUTH OF HUNAN

作　　者：徐驰[1] 李明[1] 

机构地区：[1]中国科学院上海冶金研究所

出　　处：《地质找矿论丛》1993年第3期104-111,共8页Contributions to Geology and Mineral Resources Research

摘　　要：人工神经网络和模式识别(包括主成分分析和非线性映照方法)应用于化探异常评价.样本取自湖南南部不同矿点,特征变量包括化学成分Ph、Mo、As、Sh、Ni、Sn以及物理和地质变量.二种方法对训练样本的分类正确率达100%.据此模型预报了若干个矿点为锡矿区.Artifial neural network and pattern recognition (including principal component analysis and nonlinear mapping) methods have been applied to the evaluation of geochemical anomalies. The samples are taken from different prospects in the south of Hunan. The distinct variations are their chemical compositions such as Pb, Mo As Sb Ni Sn etc., as well as their physical and geological characteristics. The correct classification rate is 100% for training samples by the two methods, and some targets are predicted as potential Sn ore-field.

关 键 词：模式识别 人工神经网络 地球化学 

分 类 号：P632[天文地球—地质矿产勘探]