Muhammad Ahsan M.; T. Celik; B. Genc
Abstract
The distribution of stream sediments is usually considered as an important and very useful tool for the early-stage exploration of mineralization at the regional scale. The collection of stream samples is not only time-consuming but also very costly. However, the advancements in space remote sensing ...
Read More
The distribution of stream sediments is usually considered as an important and very useful tool for the early-stage exploration of mineralization at the regional scale. The collection of stream samples is not only time-consuming but also very costly. However, the advancements in space remote sensing has made it a suitable alternative for mapping of the geochemical elements using satellite spectral reflectance. In this research work, 407 surface stream sediment samples of the zinc (Zn) and lead (Pb) elements are collected from Central Wales. Five machine learning models, namely the Support Vector Regression (SVR), Generalized Linear Model (GLM), Deep Neural Network (DNN), Decision Tree (DT), and Random Forest (RF) regression, are applied for prediction of the Zn and Pb concentrations using the Sentinel-2 satellite multi-spectral images. The results obtained based on the 10 m spatial resolution show that Zn is best predicted with RF with significant R2 values of 0.74 (p < 0.01) and 0.7 (p < 0.01) during training and testing. However, for Pb, the best prediction is made by SVR with significant R2 values of 0.72 (p < 0.01) and 0.64 (p < 0.01) for training and testing, respectively. Overall, the performance of SVR and RF outperforms the other machine learning models with the highest testing R2 values.
Saeed Mojeddifar; Hojatollah Ranjbar; Hossain Nezamabadipour
Abstract
The main problem associated with the traditional approach to image classification for the mapping of hydrothermal alteration is that materials not associated with hydrothermal alteration may be erroneously classified as hydrothermally altered due to the similar spectral properties of altered and unaltered ...
Read More
The main problem associated with the traditional approach to image classification for the mapping of hydrothermal alteration is that materials not associated with hydrothermal alteration may be erroneously classified as hydrothermally altered due to the similar spectral properties of altered and unaltered minerals. The major objective of this paper is to investigate the potential of a neuro-fuzzy system in overcoming this problem. The proposed system is applied to the northwestern part of the Kerman Cenozoic Magmatic Arc (KCMA), which hosts many areas of porphyry and vein-type copper mineralization. A software program based on an Adaptive Neuro-Fuzzy Inference System (ANFIS) was developed using the MATLAB ANFIS toolbox. The ANFIS program was used to classify Advanced Space-borne Thermal Emission and Reflection Radiometer (ASTER) data based on the spectral properties of altered and unaltered rocks. The ANFIS result was then compared with other classified images based on artificial neural networks (ANN) and the maximum likelihood classifier (MLC). The verification of the results, based on field and laboratory investigations, revealed that the ANFIS method produces a more accurate map of the distribution of alteration than that obtained using ANN or MLC.