Estimation of Iron concentration by using a support vector machineand an artificial neural network - the case study of the Choghart deposit southeast of Yazd, Yazd, Iran

Estimation of the metal value in the metallic deposits is one of the important factors to evaluate the deposits in exploration studies andmineral processing. Therefore, one accurate estimator is essential to obtain a fine insight into the accumulation of the ore body. Thereare geostatistical methods for the estimation of the concentration of iron which performance of these models is complexity of analysis.The support vector machine (SVM) is by far one of the most robust artificial intelligence techniques used successfully for predictionsand estimations of deposits because of its ability to generalize. Keeping this is view, the aim of this article is to use the SVM and backpropagation neural networks (BPNN) to estimate the concentration of the iron element in the Choghartdeposit, in Iran. Comparing theobtained results with those of the validation process demonstrates that the SVM method is faster than the BPNN method and is moreprecise for the estimation of the iron concentration in the Choghartmine. The results of this study show that artificial intelligence–based models can evaluate the iron concentration with an acceptable accuracy.