Traditional sheep identification is based on ear tags. However, the application of ear tags not only causes stress to the animals but also leads to loss of ear tags, which affects the correct recognition of sheep identity. In contrast, the acquisition of sheep face images offers the advantages of being non-invasive and stress-free for the animals. Nevertheless, the extant convolutional neural network-based sheep face identification model is prone to the issue of inadequate refinement, which renders its implementation on farms challenging. To address this issue, this study presented a novel sheep face recognition model that employs advanced feature fusion techniques and precise image segmentation strategies. The images were preprocessed and accurately segmented using deep learning techniques, with a dataset constructed containing sheep face images from multiple viewpoints (left, front, and right faces). In particular, the model employs a segmentation algorithm to delineate the sheep face region accurately, utilizes the Improved Convolutional Block Attention Module (I-CBAM) to emphasize the salient features of the sheep face, and achieves multi-scale fusion of the features through a Feature Pyramid Network (FPN). This process guarantees that the features captured from disparate viewpoints can be efficiently integrated to enhance recognition accuracy. Furthermore, the model guarantees the precise delineation of sheep facial contours by streamlining the image segmentation procedure, thereby establishing a robust basis for the precise identification of sheep identity. The findings demonstrate that the recognition accuracy of the Sheep Face Mask Region-based Convolutional Neural Network (SFMask R-CNN) model has been enhanced by 9.64% to 98.65% in comparison to the original model. The method offers a novel technological approach to the management of animal identity in the context of sheep husbandry.

Grassland ecosystems can greatly contribute to the global carbon cycle and ecological balance. Among them, the above-ground biomass (AGB) can serve as one of the most important indicators to assess the grassland productivity and ecosystem health. Current AGB estimation can be hindered by the single data sources, redundant feature extraction, and inadequate capture of complex nonlinear relationships. It is often required for the accurate evaluation of the grassland ecological health response to climate change. In this study, a rapid and accurate AGB estimation was proposed to fuse the GF-1 and Sentinel-2 remote sensing images. The Gegentala desert grassland was taken as the research area. GF-1 images were captured with the high spatial resolution (up to 2m for panchromatic bands). The fine-scale surface details were obtained with the limited spectral resolution. In contrast, Sentinel-2 images maintained the spatial consistency at 10m or higher. The rich spectral information was then provided for the blue, green, red, near-infrared, and shortwave-infrared bands, in order to monitor the vegetation status and ecosystem. Both GF-1 and Sentinel-2 images were fused to balance the spatial resolution and spectral characteristics. The quality of the vegetation index was significantly improved to extract the texture feature. Data preprocessing involved the geometric correction, cropping, mosaicking, and band resampling using SNAP and ArcGIS, particularly for the spatial alignment between GF-1 and Sentinel-2 images. The GF-1 data were radiometrically calibrated using absolute calibration coefficients from the China Centre for Resources Satellite Applications. Atmospheric correction was followed via the FLAASH model. Cloud-contaminated pixels were then removed to combine the thresholding and visual interpretation. As such, high consistency and accuracy were achieved for the subsequent feature extraction. The vegetation indices were also calculated to extract the texture features. Specifically, the conventional indices, such as NDVI and SAVI, were derived from the GF-1 images, while the additional indices from Sentinel-2 images were derived using shortwave-infrared and red-edge bands. Texture features (e.g., mean, variance, and homogeneity) were extracted from blue, green, red, and near-infrared bands via the gray-level co-occurrence matrix (GLCM). The optimal parameters were determined using window sizes from 3×3 to 11×11. Random forest (RF) importance evaluation was combined with optimal subset regression in order to remove the redundant features. The high-quality input variables were provided for modeling. An RF regression and a multi-scale convolutional neural network (MCNN) model were developed after feature selection. The variables of the RF model were selected according to the feature importance scores. Some parameters, such as the number of trees and the maximum depth, were optimized via Bayesian optimization. A better performance was achieved in the coefficient of determination (R²) of 0.77 and a root mean square error (RMSE) of 29.59 g/m². The multi-scale convolutional neural network (MCNN) model was utilized with 3×3 to 9×9 multi-scale convolution kernels. A multi-head attention mechanism was used to capture the multi-scale and complex nonlinear features. Residual connections and global average pooling were integrated to enhance the feature fusion efficiency and robustness. Superior performance (R²=0.81, RMSE=28.49 g/m²) was achieved to capture the complex nonlinear relationships and multi-scale features, particularly in the high-AGB regions. The MCNN model was applied to the Gegentala grassland, Inner Mongolia, China. An AGB spatial distribution map was generated with an overall mean of 51.54 g/m² and a standard deviation of 23.64 g/m², indicating the mild desertification in the region. Spatial analysis revealed that the lower biomass was found in the northwest and southwest, whereas the higher biomass was found in the north and east. There were significant impacts of the topography, land use, and human activities on the grassland degradation. The GF-1 and Sentinel-2 images were utilized to extract the vegetation indices and texture features. The sensitivity of regression models was enhanced for grassland conditions. This finding can provide an accurate AGB inversion in the desert grasslands. The reliable data support can also be offered for the ecological health during desertification monitoring, particularly for the decision-making on the ecological protection.

Grassland can provide the abundant forage and feed resources for the livestock industry, in order to maintain the ecological balance and biodiversity. One special types of the grassland, desert steppe is located at the transitional zone between grasslands and deserts, particularly with the relatively fragile ecosystem at risk of desertification. Aboveground biomass is one of the most important indicators to monitor the community structure and function in the grassland. However, the traditional estimation of aboveground biomass cannot fully meet the monitoring needs of desert grassland in a large area, due to the time-consuming, destructiveness and laborious. Satellite multi-spectral remote sensing can be expected to serve as such application against the clouds and resolution. In this study, non-destructive and accurate estimation was performed on the aboveground biomass in the desert grassland, in order to improve the monitoring level and utilization efficiency. The study area was taken from the desert grassland at Wulan Town, Etuoke Banner, Ordos City, Inner Mongolia, China. A drone was utilized to capture the hyperspectral data in the study area. Sample plots were established to collect the aboveground biomass data. A series of preprocessing was carried out on the hyperspectral datasets. Firstly, the average reflectance of each sample plot was precisely calculated to standardize the data. Subsequently, the advanced techniques of noise reduction were applied to eliminate any potential noise interference, particularly for the integrity and reliability of data. Principal component analysis (PCA) was then utilized to reduce the dimensionality. Three principal components were extracted successfully, including PC1, PC2, and PC3. These principal components were effectively condensed to highlight the key spectral features in the high-dimensional hyperspectral data. In parallel, 16 vegetation indices were calculated using the reflectance data. These indices were widely recognized in the field of vegetation research, in order to characterize the physiological and ecological status of the vegetation. After that, the correlation analysis was conducted among the principal components, vegetation indices, full-band reflectance data, and AGB. The relationships among these variables were then obtained to identify the most significant influencing factors on the AGB. A genetic algorithm was employed to further optimize the feature set. This algorithm was inspired by the principles of natural evolution, indicating the strong global searching. Finally, an optimal combination of optimal features was selected after continuous iteration and evaluation, including PC1, PC3, NDVI, NDRE. Among them, the specific bands were in the ranges of 536-557 nm, 673-690 nm, and 703-715 nm, respectively. According to these selected features, different estimation models of aboveground biomass were developed for the desert grasslands using Random Forest, BP Neural Network, and LASSO regression. A ten-fold cross-validation was applied to evaluate the performance of the improved model. The results demonstrate that the better performance of the improved model was achieved in the machine learning with the spectral features that selected by the genetic algorithm. Among them, the LASSO model exhibited the greatest performance, indicating R²=0.76, an increase of 65.2%, RMSE=0.05 kg/m², an improvement of 28.6%, MAE (mean absolute error)=0.04 kg/m², an increase of 20%, NRMSE (normalized root mean square error)=0.12, and an improvement of 36.8%. The BP Neural Network model performed the best, with R²=0.81, RMSE=0.04 kg/m², MAE=0.04 kg/m², and NRMSE=0.11. A consistence was found between the estimation and mapping of desert grassland AGB with the BPNN model and the actual distribution of vegetation. Therefore, the UAV-based hyperspectral data can be expected to construct an AGB estimation model for the desert grasslands. The finding can provide a scientific basis to formulate the grazing plans, in order prevent the overgrazing from the desertification in sustainable ranches.