Exploration
Zohre Hoseinzade; Mohammad Hassan Bazoobandi
Abstract
Anomaly detection is the process of recognizing patterns in data that differ from the typical behavior. In geochemistry, this involves identifying hidden patterns and unusual components within the context of exploratory target identification. This issue is particularly significant when limited information ...
Read More
Anomaly detection is the process of recognizing patterns in data that differ from the typical behavior. In geochemistry, this involves identifying hidden patterns and unusual components within the context of exploratory target identification. This issue is particularly significant when limited information is available about the area of interest. Therefore, employing methods that can aid in the exploration process under such conditions and with limited data is highly valuable. In this study, the Deep-Embedded Self-Organizing Map (DE-SOM), an unsupervised deep learning approach, was used to detect geochemical anomalies. The research focused on identifying multivariate geochemical anomalies in the Moalleman region. After detecting the region's geochemical anomalies, the effectiveness of the algorithm was assessed alongside two other types of SOM algorithms. For this purpose, the prediction area plot was utilized, with the intersection points for DE-SOM, Batch SOM, and SOM were determined to be 0.75, 0.67, and 0.65, respectively. The multivariate geochemical anomaly in the Moalleman area shows a good correlation with known mineral occurrences and the andesite and dacite units. Based on this, it can be stated that the DE-SOM method is a useful tool for identifying anomalies and patterns associated with mineralization.
Environment
B. Shokouh Saljoughi; A. Hezarkhani
Abstract
The Shahr-e-Babak district, as the studied area, is known for its large Cu resources. It is located in the southern side of the Central Iranian volcano–sedimentary complex in SE Iran. Shahr-e-Babak is currently facing a shortage of resources, and therefore, mineral exploration in the deeper and ...
Read More
The Shahr-e-Babak district, as the studied area, is known for its large Cu resources. It is located in the southern side of the Central Iranian volcano–sedimentary complex in SE Iran. Shahr-e-Babak is currently facing a shortage of resources, and therefore, mineral exploration in the deeper and peripheral spaces has become a high priority in this area. This work aims to identify the geochemical anomalies associated with the Cu mineralization using the Spectrum–Area (S–A) multi-fractal and Wavelet Neural Network (WNN) methods. At first, the Factor Analysis (FA) is applied to integrate the multi-geochemical variables of a regional stream sediment dataset related to major mineralization elements in the studied area. Then the S–A model is applied to decompose the mixed geochemical patterns obtained from FA and compare with the results obtained from the WNN method. The S–A model, based on the distinct anisotropic scaling properties, reveals the local anomalies due to the consideration of the spatial characteristics of the geochemical variables. Most of the research works show that the capability (i.e. classification, pattern matching, optimization, and prediction) of an ANN considering its successful application is suitable for inheriting uncertainties and imperfections that are found in mining engineering problems. In this paper, an alternative method is presented for mineral prospecting based on the integration of wavelet theory and ANN or wavelet network. The results obtained for the WNN method are in a good agreement with the known deposits, indicating that the WNN method with Morlet transfer function consists of a highly complex ability to learn and track unknown/undefined complicated systems. The hybrid method of FA, S–A, and WNN employed in this work is useful to identify anomalies associated with the Cu mineralization for further exploration of mineral resources.
Environment
B. Shokouh Saljoughi; A. Hezarkhani; E. Farahbakhsh
Abstract
The most significant aspect of a geochemical exploration program is to define and separate the anomalous values from the background. In the past decades, geochemical anomalies have been identified by means of various methods. Most of the conventional statistical methods aiming at defining the geochemical ...
Read More
The most significant aspect of a geochemical exploration program is to define and separate the anomalous values from the background. In the past decades, geochemical anomalies have been identified by means of various methods. Most of the conventional statistical methods aiming at defining the geochemical concentration thresholds for separating anomalies from the background have limited the efficiency in the areas with complex geological settings. In this work, three methods including the Concentration-Area (C-A) and Spectrum-Area (S-A) fractal models, and the U-statistic method are applied to identify the geochemical anomalies in Avanj porphyry system due to a complex geological and tectonic setting. The results obtained show that the S-A and U-statistic methods present more acceptable outputs than the C-A method. The C-A model acts well to identify the geochemical anomalies within a region including a simple geochemical background; however, the model has limitations within a region including a complex geological setting, where each sub-area is characterized by different geochemical fields. The U-statistic method, by considering the location of sampling points, their spatial relation, and radius of influence for each point in the estimation of anomaly location, overcomes the limitations of the C-A model. The S-A model is a powerful tool to decompose mixed geochemical patterns into a geochemical anomaly map and a varied geochemical background map. The output of this method shows the analysis of geochemical data in the frequency domain, which can provide new exploratory information that may not be revealed in the spatial domain. Eventually, it can be pointed out that the accuracy of the S-A fractal model for determining the thresholds is higher than the other two methods mentioned.
