Abstract:The Baiyanghe uranium deposit is a currently important medium-sized deposit in the Xuemisitan area, Xinjiang. The hydrothermal alteration in this deposit is closely related to the uranium mineralization of the deposit. In this study, hyperspectral data are collected from drill cores in the Baiyanghe uranium deposit using a FieldSpec4 visible-shortwave infrared spectrometer to study the hydrothermal alteration. The results reveal that the altered mineral assemblages have obvious zonation characteristics: (1) the upper section comprises long-wavelength illite and minor hematite and montmorillonite; (2) the middle section contains three types of illite (long-, mediumand short-wavelength illite) and hematite; and (3) the lower section includes short-wavelength illite, chlorite and carbonate. Additionally, the variety in the characteristic absorption-peak wavelength of illite at 2200 nm gradually shifts to shorter wavelength and ranges between 2195 nm and 2220 nm with increasing depth, while the SWIR-IC (short-wavelength infrared illite crystallinity, a dimensionless quantity) of the drill holes gradually increases from 0.2 to 2.1. These patterns reflect the hydrothermal fluid activity in the deposit, which features relatively high-temperature, high-pressure hydrothermal fluid in the deeper section and low-temperature, low-pressure hydrothermal fluid in the shallower section. Additionally, the uranium mineralization is located near the fracture zone, which represents the center of hydrothermal fluid activity or mineralization. This area has abundant alteration minerals, and the minerals illite (short-and medium-wavelength), hematite and fluorite can be used as uranium-prospecting indicators for uranium exploration in the deeper sections of the Baiyanghe uranium deposit.

No abstract

No abstract

Deep learning is a popular topic in machine learning and artificial intelligence research and has achieved remarkable results in various fields. In geological remote sensing, mineral mapping is an appealing application of hyperspectral remote sensing for geological surveyors. Whether deep learning can improve the mineral identification ability in hyperspectral remote sensing images, especially for the discrimination of spectrally similar and intimately mixed minerals, needs to be evaluated. In this study, shortwave airborne spectrographic imager (SASI) hyperspectral images of the Baiyanghe uranium deposit in Northwestern Xinjiang, China, were used as experimental data. Three deep neural network (DNN) models were designed: a fully connected neural network (FCNN), a one-dimensional convolutional neural network (1D CNN), and a one-dimensional and two-dimensional convolutional neural network (1D and 2D CNN). A sample dataset containing five minerals was constructed for model training and validation, which was divided into training, validation and test sets at a ratio of 6:2:2. The final test accuracies of the FCNN, 1D CNN, and 1D and 2D CNN were 91.24%, 93.67% and 94.77%, respectively. The three DNNs were used for mineral identification and mapping of SASI hyperspectral images of the Baiyanghe uranium mining area. The mapping results were compared with the mapping results of the support vector machine (SVM) and the mixture-tuned matched filtering (MTMF) method. Combined with the ground spectral data obtained by the spectrometer, spectral verification and interpretation were carried out on sections that the two kinds of methods identified differently. The verification results show that the mapping results of the 1D and 2D CNN were more accurate than those of the other methods. More importantly, for minerals with similar spectral characteristics, such as short-wavelength white mica and medium-wavelength white mica, the 1D and 2D CNN model had a more accurate discrimination effect than the other DNN models, indicating that the introduction of spatial information can improve the mineral identification ability in hyperspectral remote sensing images. In general, CNNs have good application prospects in geological mapping of hyperspectral remote sensing images and are worthy of further development in future work.

No abstract