Search

In recent years, grassland ecosystems have faced increasingly severe desertification, which has caused continuous changes in the vegetation composition in grassland ecosystems. Therefore, effective research on grassland plant taxa is crucial to exploring the process of grassland desertification. This study proposed a solution by constructing a UAV hyperspectral remote sensing system to collect the hyperspectral data of various species in desert grasslands. This approach overcomes the limitations of traditional grassland survey methods such as a low efficiency and insufficient spatial resolution. A streamlined 2D-CNN model with different feature enhancement modules was constructed, and an improved depth-separable convolution approach was used to classify the desert grassland plants. The model was compared with existing hyperspectral classification models, such as ResNet34 and DenseNet121, under the preprocessing condition of data downscaling by combining the variance and F-norm2. The results showed that the model outperformed the other models in terms of the overall classification accuracy, kappa coefficient, and memory occupied, achieving 99.216%, 98.735%, and 16.3 MB, respectively. This model could effectively classify desert grassland species. This method provides a new approach for monitoring grassland ecosystem degradation. [ABSTRACT FROM AUTHOR]

Grassland ecosystems are an important part of terrestrial ecosystems and are important for building ecological barriers, promoting the pastoral economy, and maintaining social stability. In recent decades, grasslands in northern China have undergone extensive degradation due to the combined effects of global climate change and the anthropogenic overuse of grasslands. An understanding of the spatial distribution of grassland degradation species is helpful for evaluating the process of grassland degradation and formulating appropriate protective measures. This is important for grassland degradation monitoring. To address the limitations of traditional ground surveys and realize intelligent remote sensing grassland degradation monitoring tasks, we use unmanned aerial vehicle (UAV) hyperspectral remote sensing technology to collect data on vegetation species in desert grasslands. In this paper, we propose a local-global feature enhancement network (LGFEN) for the classification of desert grassland species. The method uses the local feature enhancement (LFE) module and global feature enhancement (GFE) module to extract local and spatial information from hyperspectral images (HSIs), respectively. In addition, the introduction of the convolutional block attention module (CBAM) refines the features of HSIs, improving the stability of the classification performance. The results show that the proposed method has superior classification performance compared with existing HSI classification methods. With only 10 training samples per class, the overall accuracy, average accuracy, and kappa coefficient of the proposed method were 98.61%, 97.61%, and 0.9815, respectively. The proposed method provides a new approach for high-precision and high-efficiency dynamic monitoring of grassland ecosystems. • A local-global feature enhancement network (LGFEN) is proposed. • Improved efficiency of grassland degradation monitoring. • The LFE module is proposed to implement global feature extraction. • Compared with existing methods, LGFEN has better performance. [ABSTRACT FROM AUTHOR]

Natural grassland is an important ecological barrier in northern China and using mechanised improvement methods to restore degraded natural grassland is significant. This paper aimed to evaluate the working performance of different very narrow tines through full-factorial experiments, and provide basic references for design novel and specialised tillage tools applicable to natural grasslands. The thickness, cutting edge angle, and rake angle were chosen as the independent variables, and related working resistance and soil disturbance indicators were selected as the dependent variables. Different shank-type tines and a test bench were designed and manufactured. Field experiments under different working depths were conducted. The results showed that the thickness, rake angle, and cutting edge angle all had statistically significant influences on the working resistance (P < 0.05), and interaction functions were found between these three factors. The soil overturning rate, soil bulkiness value, and soil disturbance coefficient created by the tines were in the ranges of 0.5–14.5%, 12–40%, and 50–68%, respectively. The tine with the thickness of 14 mm, the rake angle of 45°, and the cutting edge angle of 60° provided the best working performance. The grassland surface disturbance situation, soil overturning rate, disturbed cross-section area, soil bulkiness value, and soil disturbance coefficient well described the disturbance situation. The working depth and geometrical parameters of the tines all had influence on the working resistance and soil disturbance which should be considered together as the evaluation factors of the working performance of special tines for tilling natural grasslands. • Thickness, rake angle, and chamfer angle all significantly affect working resistance. • Soil disturbance coefficient of the grassland produced by shank-type tines is 50–68%. • Shank-type tine with chamfers cause low soil disturbance and small roots' damage. • Having cutting edge or not causes big differences in the soil overturning rate. • Rake angle of 45°, chamfer angle of 60°, thickness of 14 mm are optimum combination. [ABSTRACT FROM AUTHOR]