Browsing herbivores improve the state and functioning of savannas: A model assessment of alternative land-use strategies

Research on Classification of Grassland Degeneration Indicator Objects Based on UAV Hyperspectral Remote Sensing and 3D_RNet-O Model

Real-time and high-precision land cover classification is the foundation for efficient and quantitative research on grassland degradation using remote sensing techniques. In view of the shortcomings of manual surveying and satellite remote sensing, this study focuses on the identification and classification of grass species indicating grassland degradation. We constructed a UAV-based hyperspectral remote sensing system and collected field data in grassland areas. By applying artificial intelligence technology, we developed a 3D_RNet-O model based on convolutional neural networks, effectively addressing technical challenges in hyperspectral remote sensing identification and classification of grassland degradation indicators, such as low reflectance of vegetation, flat spectral curves, and sparse distribution. The results showed that the model achieved a classification accuracy of 99.05% by optimizing hyperparameter combinations based on improving residual block structures. The establishment of the UAV-based hyperspectral remote sensing system and the proposed 3D_RNet-O classification model provide possibilities for further research on low-altitude hyperspectral remote sensing in grassland ecology.

A shift from cattle to camel and goat farming can sustain milk production with lower inputs and emissions in north sub-Saharan Africa's drylands

Climate change is increasingly putting milk production from cattle-based dairy systems in north sub-Saharan Africa (NSSA) under stress, threatening livelihoods and food security. Here we combine livestock heat stress frequency, dry matter feed production and water accessibility data to understand where environmental changes in NSSA's drylands are jeopardizing cattle milk production. We show that environmental conditions worsened for ∼17% of the study area. Increasing goat and camel populations by ∼14% (∼7.7 million) and ∼10% (∼1.2 million), respectively, while reducing the dairy cattle population by ∼24% (∼5.9 million), could result in ∼0.14 Mt (+5.7%) higher milk production, lower water (-1,683.6 million m³, -15.3%) and feed resource (-404.3 Mt, -11.2%) demand-and lower dairy emissions by ∼1,224.6 MtCO₂e (-7.9%). Shifting herd composition from cattle towards the inclusion of, or replacement with, goats and camels can secure milk production and support NSSA's dairy production resilience against climate change.