Integrating Geophysical Attributes with New Cuckoo Search Machine-Learning Algorithm to Estimate Silver Grade Values–Case Study: Zarshouran Gold Mine

The exploration methods are divided into the direct and indirect categories. Among these, the indirect geophysical methods are more time- and cost-effective compared with the direct methods. The target of the geophysical investigations is to obtain an accurate image from the underground features. The Induced polarization (IP) is one of the common methods used for metal sulfide ore detection. Since metal ores are scattered in the host rock in the Zarshouran mine area, IP is considered as a major exploration method. Parallel to IP, the resistivity data gathering and processing are done to get a more accurate interpretation. In this work, we try to integrate the IP/RS geophysical attributes with borehole grade analyses and geological information using the cuckoo search machine-learning algorithm in order to estimate the silver grade values. The results obtained show that it is possible to estimate the grade values from the geophysical data accurately, especially in the areas without drilling data. This reduces the costs and time of the exploration and ore reserves estimation. Comparing the results of the intelligent inversion with the numerical methods, as the major tools to invert the geophysical data to the ore model, demonstrate a superior correlation between the results.