Search Results (2)

The large-sized Tarangaole uranium deposit and its neighboring Daying and Nalinggou deposits, located in the northeastern margin of the Ordos Basin, constitutes a major uranium resource base in northern China. In order to further clarify the sedimentary material source, uranium source and regional sediment–tectonic setting of the uranium-fed clastic rocks (i.e., Zhiluo Formation(J₂z)) in the district, this paper carried out whole-rock geochemistry, heavy minerals composition and in situ U-Pb dating of detrital zircons for sandstones from the lower section of the Zhiluo Formation. The results have shown that the average chemical differentiation index (CIA) for the host rocks is 73.16 and the chemical weathering degree is moderate. Heavy minerals are mainly composed of ilmenite, garnet, chlorpyrite, zircon, pyrite, apatite, hematite, etc. The U-Pb dating of detrital zircon generally indicates three age peaks, i.e., 260~Ma, 1850~Ma and 2450~Ma, respectively. In conclusion, the source rocks may have been formed at active continental margins, e.g., in a continental margin arc environment. The sedimentary materials mainly come from khondalite series, TTGs, granulite, and mafic–ultramafic intrusive rocks distributed among the Daqing–Ula Mountains and adjacent areas, etc. The Late Paleozoic U-rich intermediate and acidic magmatic rocks spreading over the eastern part of the Ula–Daqing and Wolf mountains have provided the main uranium sources for the formation of major U deposits in the northern Ordos Basin. Full article

Lithology identification is an essential fact for delineating uranium-bearing sandstone bodies. A new method is provided to delineate sandstone bodies by a lithological automatic classification model using machine learning techniques, which could also improve the efficiency of borehole core logging. In this contribution, the BP neural network model for automatic lithology identification was established using an optimized gradient descent algorithm based on the neural network training of 4578 sets of well logging data (including lithology, density, resistivity, natural gamma, well-diameter, natural potential, etc.) from 8 boreholes of the Tarangaole uranium deposit in Inner Mongolia. The softmax activation function and the cross-entropy loss function are used for lithology classification and weight adjustment. The lithology identification prediction was carried out for 599 samples, with a prediction accuracy of 88.31%. The prediction results suggest that the model is efficient and effective, and that it could be directly applied for automatic lithology identification in sandstone bodies for uranium exploration. Full article