Search Results (2)

Unregulated livestock breeding and grazing can degrade grasslands and damage the ecological environment. The combination of remote sensing and artificial intelligence techniques is a more convenient and powerful means to acquire livestock information in a large area than traditional manual ground investigation. As a mainstream remote sensing platform, unmanned aerial vehicles (UAVs) can obtain high-resolution optical images to detect grazing livestock in grassland. However, grazing livestock objects in UAV images usually occupy very few pixels and tend to gather together, which makes them difficult to detect and count automatically. This paper proposes the GLDM (grazing livestock detection model), a lightweight and high-accuracy deep-learning model, for detecting grazing livestock in UAV images. The enhanced CSPDarknet (ECSP) and weighted aggregate feature re-extraction pyramid modules (WAFR) are constructed to improve the performance based on the YOLOX-nano network scheme. The dataset of different grazing livestock (12,901 instances) for deep learning was made from UAV images in the Hadatu Pasture of Hulunbuir, Inner Mongolia, China. The results show that the proposed method achieves a higher comprehensive detection precision than mainstream object detection models and has an advantage in model size. The $mAP$ of the proposed method is 86.47%, with the model parameter 5.7 M. The average recall and average precision can be above 85% at the same time. The counting accuracy of grazing livestock in the testing dataset, when converted to a unified sheep unit, reached 99%. The scale applicability of the model is also discussed, and the GLDM could perform well with the image resolution varying from 2.5 to 10 cm. The proposed method, the GLDM, was better for detecting grassland grazing livestock in UAV images, combining remote sensing, AI, and grassland ecological applications with broad application prospects. Full article

The Erlian basin is one of the most important basins in northern China to host sandstone-type uranium deposits (SUDs), in which Bayanwula, Saihangaobi, and Hadatu are under development, to name a few. Issues such as the metallogenic mechanism and mineralization of these deposits need to be addressed throughout the mining process. Over the past several decades, 2D and 3D seismic reflection surveys have been carried out to study these typical SUDs. The seismic technique has become the most effective geophysical tool of uranium (U) exploration, and it is used to develop our understanding of the stratigraphic configuration, faults, and sandstone contents of target layers in uranium environments. In addition, seismic interpretation could yield useful suggestions regarding the subsequent drilling program in the work area. There are two seismically predictable patterns of SUDs, named “Big depression + fault” and “Large-angle unconformity + fault”, which have been established following detailed seismic research in this basin. The characteristics of these faults are as follows: (1) the “‘U’-shaped formation” is conducive to the inflow of O-U-bearing groundwater into the target sandstone; (2) the “Big depression of reductive formation” provides plenty of organic matter (containing reducing media and U pre-enrichment) to promote redox reaction mineralization; (3) “Large-angle unconformity” is favorable to the migration of reducing substances, consequently leading to an enhancement in redox U mineralization; (4) “faults with long-term activity” become rising channels for reducing the presence of fluids and gases at depth; and (5) “sandstone and its scrambled seismic facies”. The results also offer indirect evidence of a connection between hydrothermal fluids and U mineralization; a hypothesis of “hydrothermal effusion” mineralization is proposed accordingly. In conclusion, seismically produced images of geological structures and sandstone distribution could yield important information for U prospecting and mine planning; it is worth considering seismic technologies in the future exploration of SUDs. Full article