An SVM-based machine learning method for the separation of alteration zones in Sungun porphyry copper deposit

作者：Abbaszadeh Maliheh; Hezarkhani Ardeshir^*; Soltani Mohammadi Saeed

来源：Chemie der Erde, 2013, 73(4): 545-554.

DOI：10.1016/j.chemer.2013.07.001

• Fluid inclusion
• Alteration
• Statistical learning theory
• Support Vector Machine

Sungun porphyry copper deposit is in East Azarbaijan province, NW of Iran. There exist four hypogene alteration types in Sungun: potassic, propylitic, potassic-phyllic, and phyllic. Copper mineralization is essentially associated more with the potassic and less with the phyllic alterations and their separation is, therefore, quite important. This research has tried to separate these two alteration zones in Sungun porphyry copper deposit using the Support Vector Machine (SVM) method based on the fluid inclusion data, and seven variables including homogenization temperatures, salinity, pressure, depth, density and the Cu grade have been measured and calculated for each separate sample. To apply this method, use is made of the radial basis RBF) as the kernel function. The best values for lambda and C (the most important SVM parameters) that perform well in the training and test data are 0.0001 and 1, respectively. If these values for lambda and Care applied, the phyllic and potassic alteration zones in the training and test data will be separated with an accuracy of about 95% and 100%, respectively. This method can help geochemists in separating the alteration zones because classifying and separating samples microscopically is not only very hard, but also quite time and money consuming.

• 出版日期2013