تلفيق و مدلسازي چند متغيره داده هاي ژئوفيزيك با حفاريهاي اكتشافي انجام شده در كانسارهاي مس پورفيري علي آباد و دره زرشك جهت شناسايي كليدهاي اكتشافي

چكيده انگليسي :

Multivariate Modeling of Geophysical Data Integrated with ExploratoryDrilling Data for Aliabad and Darehzereshk Porphyry Copper Deposits in Order to Exploit the Exploratory Associative Rules Esmaiel Ghasemi e ghasemy@ec iut ac ir Date of Submission 2012 01 9 Department of Mining Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Ahmadreza Mokhtari ar mokhtari@cc iut ac ir Nader Fathianpoor fathian@cc iut ac irAbstractSince most of copper deposits in Iran are porphyry copper deposit optimal exploration of porphyry copperdeposits of Iran has great importance In the exploration these types of deposits geophysical and geologicalperceptions are powerful techniques and provide useful information for researchers to determining thelocation of mineralization separation high grade zones from background and determination optimallocation of exploratory boreholes Due to the high complexity of earth structure and gang mineralization interpreting and analyzing of this raw data is very difficult work that sometimes this complexity isconfusing object for researcher We propose automatic classification as a way to tackle this problem Thisproblem can be regarded as a classification problem that goal is discrete high grade zone from low gradezone background In the last decades researchers try to use the machine learning methods instead ofclassical methods that can reduce human error in the classification problems Besides automatic proceduresare based on formalized data processing schemes which render them reproducible and can be used in othersimilar situation Thus using multivariate statistical analysis and supervised classification methods cansignificantly reduce the risk level of decision making for the researchers With the help of geophysical dataincluding induce polarization resistivity magnetic measurement and geological data including lithologyand alteration in this thesis for separation high grade zones from low grade zones waste in porphyrycopper deposits the three supervised classification methods include Support Vector Machine SVM Linear Discriminate Analysis LDA and Quadratic Discriminate Analysis QDA were used Supervisedclassification methods have three steps in first step the model have been trained and learned each exampledata belongs to which group with use of training data afterwards in second step the model has been crossvalidate and in final step the model has been test by test data Linear Discriminate Analysis and QuadraticDiscriminate Analysis are two classical methods that have been used in a lot of variety classification studiesin three last decades and expose good performance in majority of them The goal of discriminant analysis isto obtain rules that describe the separation between groups of observations Support Vector Machines arelearning systems that use a hypothesis space of linear functions in a high dimensional feature space trainedwith a learning algorithm from optimization theory that implements a learning bias derived from statisticallearning theory This learning strategy introduced by Vapnik and co workers is a principled and verypowerful method that in the few years since its introduction has already outperformed most other systems ina wide variety of applications and has good generalization ability compared to other methods Informationand data of two Aliabad and Darehzereshk porphyry copper deposit have been analyzed in this thesis InAliabad deposit SVM method with accuracy equal to 80 in comparison QDA method with 69 accuracyand LDA method with 67 accuracy provided Better performance in classification of data InDarehzereshk deposit SVM method with an accuracy of 90 in comparison QDA and LDA methods with81 and 82 accuracy has been more successful in classification of data Keywords Aliabad copper deposit Darehzereshk copper deposit Multivariate Supervised Classification Discriminant Analysis Support Vector Machine

قاسمي، اسماعيل

تلفيق و مدلسازي چند متغيره داده هاي ژئوفيزيك با حفاريهاي اكتشافي انجام شده در كانسارهاي مس پورفيري علي آباد و دره زرشك جهت شناسايي كليدهاي اكتشافي

كلاس بندي نظارتي چند متغيره , آناليز تمايز , ماشين بردار پشتيبان