Search

This study illustrates the application of a geometric average integration of aeromagnetic, radiometric and satellite imagery data over a region prone to Cu‐bearing mineralization at Chahargonbad area in Kerman province of Iran. Processing aeromagnetic, radiometric and Advanced Spaceborne Thermal Emission and Reflection Radiometer satellite data can provide exploratory insights about favourable zones in association with porphyry‐type ore occurrences, which can be synthesized through a combination of knowledge‐ and data‐driven approaches as a geometric average and be represented in a mineral prospectivity map. The existence of known deposits in a prospect region can facilitate the investigation of significant exploratory footprints extracted from airborne data by calculating each indicator layer's weight by plotting a prediction–area curve accompanied by a concentration–area fractal curve. Among various indicators, the most important ones are determined based on derived weights from the prediction–area plots to be synthesized in a single Cu favorability map. To fulfil this aim, indicator layers from airborne geophysics (magmatic bodies, magnetic lineaments and potassium radiometry) and remote‐sensing data (alterations such as argillic, phyllic, propylitic and iron oxide along with geological lineaments) were prepared and evaluated using the known porphyry Cu mineralization by the simultaneous plot of the concentration–area fractal model and the prediction–area curve to attain the ore prediction rate and the relevant occupied area of each map for weight assignment of indicators. The geometric average prospectivity model was applied to synthesize the leading indicators, and the result was compared with a multi‐class index overlay map. This study's significance lies in improvement of the performance of the mineral prospectivity/potential mapping after running a geometric average by a higher ore prediction rate of 79%, which has occupied 21% of the area as potential zones for further mining investigations. [ABSTRACT FROM AUTHOR]

Selection of non-deposit sites is a challenging issue affecting the application of supervised algorithms for modeling mineral exploration targets. For this, equal number of deposit and non-deposit sites has been widely applied for training purposes. In this paper, we investigated the effect of changes in the number of non-deposit sites on the effectiveness of exploration targeting models while the number of deposit sites is constant. The results obtained demonstrated that exploration targeting models are affected by the ratio of non-deposit and deposit sites. Thus, balancing between the number of deposit and non-deposit sites is an efficient way to produce more-reliable exploration targets when supervised algorithms are applied for modeling. The idea of this research came from the fact that mineralization is a rare event, and therefore, in a region of interest number of non-deposit sites is much more than that of deposit events. To illustrate the procedure proposed, we used an exploration dataset of porphyry Cu mineralization in Chahargonbad area, SE Iran. A sequence application of self-organizing map and multilayer perceptron neural network algorithm was applied to better illustration of the changing effects of the number of non-deposit sites on the ensuing exploration targeting models. • Counting of deposit and non-deposit sites is discussed for training purpose. • The number affects the ensuing exploration targeting models. • Making a balance between the two types of training data yields significant results. • Self-organizing map clustering approach leads to define non-deposit sites. [ABSTRACT FROM AUTHOR]