No abstract

No abstract

Sandstone-type uranium deposits in China are mainly found in two kinds of clastic formations: the gray clastic formations in the Lower-Middle Jurassic Series and the red clastic formations in the Cretaceous, Paleogene or Neogene (Liu et al., 1997; Chen et al., 2003; 2011). Uranium mineralization is mainly hosted by red clastic formations interlayered with gray medium-or fine-grained clastic formations. Red clastic formations are the main uranium-producing and prospecting target layers in the Erlian and Songliao Basins of northern China, where many large and medium-sized uranium deposits have been found, such as the Qianjiadian (Luo et al., 2007; Pang et al., 2010) and Baolongshan (Xu et al., 2011) deposits in the Songliao Basin and the Nuheting and Subeng deposits (Kang, 2011) in the Erlian Basin. Several small and medium-sized uranium deposits have also been found in other basins, such as the Hongshan deposit (Li et al., 2010) in the Jiudong Basin, the Dahongshan deposit (Guo et al., 2015) in the Chaoshui Basin, the Wangjiachong deposit (Jiang et al., 2017) in the Hengyang Basin and the Guojiawan deposit (Sun, 1998; Chen et al., 2011) and the Hangjinqi Deposit (Zhang et al., 2017) in the Ordos Basin. Thick red clastic formations are widespread throughout all basins in northern China and in the red basins in southern China; therefore, studies on the characteristics of uranium mineralization in red clastic formations will expand the exploration space of sandstone-type uranium resources in China. Uranium mineralization in red clastic rock formations in the Erlian and Songliao basins has been systematically studied, resulting in breakthroughs in uranium exploration. However, studies on uranium mineralization in the southwestern Ordos Basin are still relatively limited, in particular in terms of geological reactions, geological features and key ore-controlling factors. Such gaps in the

No abstract

Accurately establishing a 3D digital core model is of great significance in oil and gas production. The physical experiment method and numerical modeling method are common modeling methods. With the development of deep learning technology, a variety of deep learning algorithms have been applied to digital core modeling. The digital core modeling method based on generative adversarial neural networks (GANs) has attracted wide attention due to its good quality and simple generation process. The disadvantage of this method is that the network needs thousands of trainings to achieve acceptable results. For this reason, this paper proposes to use the pretrained GANs for digital core modeling training, which can greatly reduce the number of network training while ensuring the core modeling effect. We can use the presented method to quickly complete the training and use the trained generator model to obtain multiple digital cores. By analyzing the quality of the generated cores from multiple aspects, it is revealed that the properties of the generated cores are in good agreement with the ones of the real core samples. The results indicate the reliability of the pretrained GAN method.