Overgrazing typically leads to grassland vegetation degradation and reduction, which in turn triggers a series of ecological problems. Therefore, it is crucial to understand the effects of different Grazing Intensities (GIs) on the Vegetation Ecosystem (VE) to achieve sustainable grazing development. This study proposes a new quantitative index, the Grazing Intensity and Vegetation Cover Harmonization Index (GVCI), based on multiple indicators such as fractional vegetation cover (FVC), net primary productivity (NPP), and GI. The GVCI was used to quantify the “Harmonization and Conflict” status between GI and the VE in 39 Prefecture-Level Cities (PLCs) of the Qinghai-Tibet Plateau (QTP) and to evaluate the sustainable development level of grazing in different regions. In addition, the Random Forest (RF) model was used to simulate the GVCI development trend of various PLCs from 2015 to 2040. The results showed the following: (1) The GVCI can effectively quantify the response relationship between GI and the VE. The overall GVCI of the QTP was in the “Harmonization” state, with the proportion of areas in the “Harmonization” state fluctuating upwards. (2) The level of economic development intuitively affects the harmonization between grazing and the VE. Gross Domestic Product (GDP) is one of the important indicators of economic development level. PLCs with higher GDP levels exhibited a strong positive correlation between the GVCI and regional GDP. (3) The simulation results indicate that an increasing number of PLCs on the QTP will shift toward a “Harmonization” state. However, some PLCs in the western regions were still in an “Overload” state, and there is a need for close monitoring of their grazing activities and VE dynamics. The GVCI proposed in this study provides a novel methodology for quantifying the complex relationship between GI and the VE. It offers important scientific support for the sustainable development of grazing in ecologically fragile areas such as the QTP. The research results can be a robust scientific basis for the government to formulate reasonable grazing plans.

Accurate tree species classification using high-resolution unmanned aerial vehicle (UAV) images is crucial for forest carbon cycle research, biodiversity conservation, and sustainable management. However, challenges persist due to high interspecies feature similarity, complex canopy boundaries, and computational demands. To address these, we propose an enhanced DeepLabV3+ model integrating Object-Based Image Analysis (OBIA) and a lightweight attention mechanism. First, an OBIA-based multiscale segmentation algorithm optimizes object boundaries. Key discriminative features, including spectral, positional, and vegetation indices, are then identified using Recursive Feature Elimination with Cross-Validation (RFECV). High-precision training labels are efficiently constructed by combining Random Forest classification with visual interpretation (RFVI). The DeepLabV3+ model is augmented with a lightweight attention module to focus on critical regions while significantly reducing model parameters. Evaluations demonstrate that the improved DeepLabV3+ model achieved overall accuracy (OA) of 94.91% and Kappa coefficient (Kappa) of 92.89%, representing improvements of 2.91% and 4.11% over the original DeepLabV3+ model, while reducing parameters to 5.91 M (78.35% reduction). It significantly outperformed U-Net, PSPNet, and the original DeepLabV3+. This study provides a high-accuracy yet lightweight solution for automated tree species mapping, offering vital technical support for forest carbon sink monitoring and ecological management.

Fractional Vegetation Cover (FVC) dynamics on the Qinghai–Tibetan Plateau (QTP) are critical indicators for assessing ecosystem condition. However, uncertainties persist in the accuracy of existing FVC products over the QTP due to retrieval differences, scale effects, and limited validation data. This study utilized the Google Earth Engine platform to integrate unmanned aerial vehicle (UAV) observations, Sentinel-2, MODIS, climate, and topography datasets, and proposed a comprehensive framework incorporating dual-index screening, machine learning optimization, and multidimensional validation to systematically assess the accuracy of GEOV3, GLASS, and MuSyQ FVC products in the alpine grasslands. The dual-index screening reduced validation uncertainty by improving the spatial representativeness of ground data. To build a high-precision evaluation dataset with limited inter-class coverage, recursive feature elimination and grid search were applied to optimize five ML models, and CatBoost achieved the superior performance (R² = 0.880, RMSE = 0.122), followed by XGBoost, GBM, LightGBM, and RF models. Four validation scenarios were implemented, including direct validation using 250 m UAV plot FVC and multi-scale validation using a 10 m FVC reference aggregated to product grids. Results show that GEOV3 (R² = 0.909–0.925, RMSE = 0.082–0.103) outperformed GLASS (R² = 0.742–0.771, RMSE = 0.138–0.175) and MuSyQ (R² = 0.739–0.746, RMSE = 0.138–0.181), both of which exhibited systematic underestimation. This framework significantly enhances FVC product validation reliability, providing a robust solution for remote sensing product validation in alpine grassland ecosystems.