هادی جمشید مقدم

The studied area located in eastern Iran shows a high potential for various mineralizations, especially copper due to its tectonic activity. Remote sensing data can effectively distinguish these areas because of the sparse vegetation. Therefore, in this study, the ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) multi-spectral data was used to recognize argillic, sericite, propylitic, and iron oxide alterations associated with copper mineralization. For this purpose, two categories (porphyry copper-iron and advanced argillic-iron) related alterations were considered to perform the classification of a 2617 square kilometer area using a neural network classification algorithm. To evaluate the accuracy of the classifier, the confusion matrix was computed, which provides overall accuracy and the kappa coefficient factors for assessing classification accuracy. As a result, 64.17% and 83.5% of overall accuracy, and 0.602 and 0.807 of the kappa coefficient were achieved for the advanced argillic alterations and porphyry copper categories, respectively. Ultimately, the validation of the classifications was carried out using the normalized score (NS) equation, employing quantitative criteria. Notably, the advanced argillic class emerged with the top normalized score of 2.25 out of 4, signifying a 56% alignment with the geological characteristics of the region. Consequently, this outcome has led to the identification of favorable areas in the central and northeastern parts of the studied area.

The hyperspectral images are studied to extract the spectral signatures of the elements that comprise the image pixels (end members) and estimate their frequency. The surface reflectance spectrum is considered a linear combination of endmember spectra in linear mixing models. When internal mixing is also important, the linear model is not the answer, and non-linear algorithms should be used. The method used in this research is the generalization and improvement of Nascimento and Fan's bilinear models, known as the generalized bilinear mixing model (BPOGM). This study aims to apply and evaluate this method in the face of data with high mixing and large volumes. Therefore, the data used in this research are Hyperion data of Khoi region, which has good mineral and mineralogical indicators. First, the available pure spectra were extracted using the N-FINDR method. In addition to the excellent compatibility of the N-FINDER method, it has more ability to extract endmembers than the pixel purity index method used in linear separation. In this way, stilbite mineral (representative of zeolite group), vermiculite (representative of mica group), serpentine (representative of olivines of harzburgite and serpentinized ultramafic rocks), chlorite (representative of chlorite group), and quartz were identified. Then, using the BPOGM method, which is a solution method for the bilinear GBM model, the frequency of each end member was calculated, and the distribution map was obtained. The results of the non-linear method comply well with the geological map of the region based on mineralogical interpretations of the lithological facies (average accuracy of 78.25), which is completely acceptable at this stage of exploration work.

The hyperspectral imagery provides images in hundreds of spectral bands within different wavelength regions. This technology has increasingly applied in different fields of earth sciences, such as minerals exploration, environmental monitoring, agriculture, urban science, and planetary remote sensing. However, despite the ability of these data to detect surface features, the measured spectrum is composed of several components that make it a mixed spectrum due to the low spatial resolution observed of the employed sensors or the presence of multiple materials in its instantaneous field of view (IFOV). The existence of a mixed spectrum severely prevents the accurate processing of the hyperspectral data. Therefore, it is necessary to separate these mixtures through the so-called spectral unmixing methods. Spectral unmixing is performed to decompose a mixed pixel in hyperspectral images into a set of spectra (endmembers) and their abundances. Typically, two types of spectral mixing models (linear and nonlinear) are considered. In the linear mixing model (LMM), the reflected radiance at the sensor is the outcome of interference with one material, where a pixel is assumed to be a linear combination of endmembers weighted by their abundances. The nonlinear model, on the other hand, is used when the mixing scale is microscopic or materials are mixed intrinsically. In recent years, the linear mixing model has been a very popular model for hyperspectral processing in the last decades, and a large effort has been put into using this model for unmixing applications, resulting in an overabundance of linear unmixing methods and algorithms. Over the last decades, the linear mixing model has been utilized in the detection of minerals and their abundances. However, as early as 40 years ago, it has been observed that strong nonlinear spectral mixing effects are present in many situations, for instance, when there are multi scattering effects or intimate mineral interactions. While such nonlinear unmixing techniques have received much less attention than linear ones.
Therefore, this paper aims to give an overview of the majority of nonlinear mixing models and methods used in hyperspectral image processing, and many recent developments in this field. Besides, several of the more popular nonlinear unmixing techniques are explained in detail. In this regard, nonlinear unmixing methods can be categorized into two groups: physics-based methods and data-driven techniques. The most important methods of these two groups are divided into bilinear and multi-linear models, intimate mineral mixture models, radiosity based approaches, ray tracing, neural network, kernel methods, manifold learning, and topology methods. A comprehensive review of these methods can be found in which bilinear and multi-linear models and neural networks have become more popular among researchers over the years. The current study should give the reader that is interested in working with nonlinear unmixing techniques a reasonably good introduction into the most commonly used methods and approaches.